Search

The growing number of applications of machine learning and data mining in many domains—from agriculture to business, education, industrial manufacturing, and medicine—gave rise to new requirements for how to inspect and control the learned models. The research domain of explainable artificial intelligence (XAI) has been newly established with a strong focus on methods being applied post-hoc on black-box models. As an alternative, the use of interpretable machine learning methods has been considered—where the learned models are white-box ones. Black-box models can be characterized as representing implicit knowledge—typically resulting from statistical and neural approaches of machine learning, while white-box models are explicit representations of knowledge—typically resulting from rule-learning approaches. In this introduction to the special issue on 'Explainable and Interpretable Machine Learning and Data Mining' we propose to bring together both perspectives, pointing out commonalities and discussing possibilities to integrate them. [ABSTRACT FROM AUTHOR]

One of the traditional and current areas of application of artificial intelligence is games. To date, existing solutions for this industry are developed only by companies that collaborate with developers and have access to the application programming interface of games. Not all researchers have the opportunity to gain such access, which may limit progress in the field of artificial intelligence. One way to get around this limitation would be to apply computer vision to the image on the screen that reflects what is happening in the game. However, most modern computer vision methods use labeled data. Labeling, in turn, requires a lot of labor, time and has a high cost. When applied to computer games, the problem of training data becomes even more acute, since modern computer games periodically receive various updates and additions, after each of which it would be necessary to prepare new training data. To reduce the need for labeled data, it seems promising to use a hybrid approach that combines machine learning with knowledge representation. One such method is informed machine learning. Thus, the goal of this research is to develop a method for recognizing objects in computer games based on informed machine learning, reducing the need for labeled data, but with accuracy comparable to end-to-end methods. This article provides an overview of the current state of the art of artificial intelligence in computer games, computer vision methods based on a hybrid approach, and informed machine learning methods. An object recognition model has been developed using informed machine learning. The game Hearthstone was chosen as an application, and the task of detecting and classifying cards present on the playing field was considered. Experiments have shown that the model achieves higher accuracy than classical machine learning models, while using simpler training labels. [ABSTRACT FROM AUTHOR]

Accurately predicting potential evapotranspiration (PET) is crucial in water resource management, agricultural planning, and climate change studies. This research aims to investigate the performance of two machine learning methods, the adaptive network-based fuzzy inference system (ANFIS) and the deep belief network (DBN), in forecasting PET, as well as to explore the potential of hybridizing the ANFIS approach with the Snake Optimizer (ANFIS-SO) algorithm. The study utilized a comprehensive dataset spanning the period from 1983 to 2020. The ANFIS, ANFIS-SO, and DBN models were developed, and their performances were evaluated using statistical metrics, including R2, R adj 2 , NSE, WI, STD, and RMSE. The results showcase the exceptional performance of the DBN model, which achieved R2 and R adj 2 values of 0.99 and NSE and WI scores of 0.99 across the nine stations analyzed. In contrast, the standard ANFIS method exhibited relatively weaker performance, with R2 and R adj 2 values ranging from 0.52 to 0.88. However, the ANFIS-SO approach demonstrated a substantial improvement, with R2 and R adj 2 values ranging from 0.94 to 0.99, suggesting the value of optimization techniques in enhancing the model's capabilities. The Taylor diagram and violin plots with box plots further corroborated the comparative analysis, highlighting the DBN model's superior ability to closely match the observed standard deviation and correlation and its consistent and low-variance predictions. The ANFIS-SO method also exhibited enhanced performance in these visual representations, with an RMSE of 0.86, compared to 0.95 for the standard ANFIS. The insights gained from this study can inform the selection of the most appropriate modeling technique, whether it be the high-precision DBN, the flexible ANFIS, or the optimized ANFIS-SO approach, based on the specific requirements and constraints of the application. [ABSTRACT FROM AUTHOR]

Nowadays, lattice Boltzmann is one of the standard and exact methods of simulation in micro‐CT images of rock. However, it has a high weakness in run time. Therefore, the effort in this article is to reach a comprehensive substitute method for permeability calculation with less run time than the lattice Boltzmann method. The other purposes are the automation of processing operations, preparation of images, and in the end, the calculation of porosity. The best way to achieve these outcomes is to use hybrid artificial intelligence. In this research work, comprehensive model architecture has been used to design a hybrid artificial intelligence to be able to calculate permeability and porosity in complex images. A thousand images were randomly generated with high complexity, which makes the model comprehensive and extensible, and image processing was applied. After that, the lattice Boltzmann method as the direct simulation was selected. Finally, the convolutional neural network and multilayer perceptron based on a new and comprehensive model were evaluated for the first time; the mean squared error resulting from the evaluation of training data is 0.01, and the test data is 0.03. Expert systems have been used as a subset of artificial intelligence for automated image processing and porosity calculation. In this way, problems related to the direct implementation of classical algorithms for image processing, models, and patterns related to machine learning and needing an expert were solved to an acceptable extent, and an error of less than 5% was achieved. [ABSTRACT FROM AUTHOR]

The goal of the paper is to find means for the unification of human-machine duality in collective behavior of people and machines, by conciliating approaches that proceed in opposite directions. The first approach proceeds top-down from non-formalizable, cognitive, uncaused, and chaotic human consciousness towards purposeful and sustainable human-machine interaction. The second approach proceeds bottom-up from intelligent machines towards high-end computing and is based on formalizable models leveraging multi-agent architectures. The resulting work reviews the extent, the merging points, and the potential of hybrid artificial intelligence frameworks that accept the idea of strong artificial intelligence. These models concern the pairing of connectionist and cognitive architectures, conscious and unconscious actions, symbolic and conceptual realizations, emergent and brain-based computing, and automata and subjects. The special authors’ convergent methodology is considered, which is based on the integration of inverse problem-solving on topological spaces, cognitive modelling, quantum field theory, category theory methods, and holonic approaches. It aims to a more purposeful and sustainable human-machine interaction in form of algorithms or requirements, rules of strategic conversations or network brainstorming, and cognitive semantics. The paper addresses the reduction of the impact of AI development on ethics violation. The findings delivered are used to provide perspectives on the shaping of societal, ethical, and normative aspects in the symbiosis between humans and machines. Implementations in real practice are represented.

In the present study, an improved adaptive neuro fuzzy inference system (ANFIS) and multilayer perceptron (MLP) models are hybridized with a sunflower optimization (SO) algorithm and are introduced for lake water level simulation. The Urmia Lake water level is predicted and assessed using the potential of the proposed advanced artificial intelligence (AI) models. The sunflower optimization algorithm is implemented to find the optimal tuning parameters. The results indicated that the ANFIS-SO model with the combination of three lags of rainfall and temperature as input attributes attained the best predictability performance. The minimal values of the root mean square error were RMSE = 1.89 m and 1.92 m for the training and testing modeling phases, respectively. The worst prediction capacity was attained for the long lead (i.e., six months rainfall lag times). The uncertainty analysis showed that the ANFIS-SO model had less uncertainty based on the percentage of more responses in the confidence band and lower bandwidth. Also, different scenarios of water harvesting were investigated with the consideration of environmental restrictions and fair water allocation to stakeholders. Further, studying Urmia Lake water harvesting scenarios displayed that the 30% water harvesting scenario of the lake water improves the lake’s water level.

Recycled aggregate concrete is used as an alternative material in construction engineering, aiming to environmental protection and sustainable development. However, the compressive strength of this concrete material is considered as a crucial parameter and an important concern for construction engineers regarding its application. In the present work, the 28-days compressive strength of recycled aggregate concrete is investigated through four artificial intelligence techniques based on a meta-heuristic search of sociopolitical algorithm (i.e. ICA) and XGBoost, called the ICA-XGBoost model. Based on performance indices, the optimum among these developed models proved to be ICA-XGBoost model. Namely, findings demonstrated that the proposed ICA-XGBoost model performed better than the other models (i.e. ICA-ANN, ICA-SVR, and ICA-ANFIS models) in estimating compressive strength of recycled aggregate concrete. The suggested model can be used in construction engineering in order to ensure adequate mechanical performance of the recycled aggregate concrete and allow its safe use for building purposes. [ABSTRACT FROM AUTHOR]

The article describes the author's proposal on cognitive architecture for the development of a general-level artificial intelligent agent («strong» artificial intelligence). New principles for the development of such an architecture are proposed — a hybrid approach in artificial intelligence and bionics. The architecture diagram of the proposed solution is given and descriptions of possible areas of application are described. Strong artificial intelligence is a technical solution that can solve arbitrary cognitive tasks available to humans (human-level artificial intelligence) and even surpass the capabilities of human intelligence (artificial superintelligence). The fields of application of strong artificial intelligence are limitless — from solving current problems facing the human to completely new problems that are not yet available to human civilization or are still waiting for their discoverer. The novelty of the work lies in the author's approach to the construction of cognitive architecture, which has absorbed the results of many years of research in the field of artificial intelligence and the results of the analysis of cognitive architectures of other researchers. [ABSTRACT FROM AUTHOR]

[Display omitted] • Denoising based AI tools to examine the predictability of environmental externalities. • Comparison between denoised based traditional and AI models. • MAPE, MSE and RMSE are lower for CSD-ANN, whereas D stat is higher. • CSD-based ANN model has outperformed to forecast the PM 10. The current study attempts to compare the hybrid artificial intelligence models to forecast the environmental externalities in Saudi Arabia. We have used the denoising based artificial intelligence models to construct hybrid models. While comparing the denoising techniques, the CSD-based denoising has outperformed. However, we have used the CSD-based hybrid models. CSD-ANN and CSD-RNN are used for denoising-based artificial intelligence models, whereas CSD-ARIMA is used for denoising-based traditional models. All these models are used to check and compare their performance in terms of level and direction of prediction for PM 10. The results show that the CSD-based ANN model has a higher predictability for PM 10 levels in Saudi Arabia due to low error values and higher D stat values. In comparing original and forecasted data, the superiority of CSD-ANN is evident in predicting the PM 10 in Saudi Arabia. Hence, this hybrid model can predict the environmental externalities for non-linear and highly noised data. Moreover, the findings can be useful in achieving the sustainable development goal. [ABSTRACT FROM AUTHOR]

[Display omitted] • Hybrid AI models to forecast the natural resource prices in Saudi Arabia. • We employed six denoising methods and CSD is reporting the superiority over other methods. • CSD-RNN has confirmed the outperforming machine learning technique to forecast the prices. • The CSD-RNN forecasted technique can be used to forecast the other energy index. The prediction performance of traditional forecasting methods is low due to the high level of complexity in a series of energy prices. The present study attempts to compare the traditional regression, machine learning tools and hybrid models to conclude the outperforming model. The first step is to propose the effective denoising technique for Tadawul energy index, which has confirmed the superiority of CSD based denoising. However, we use the CSD-ARIMA, CSD-ANN, and CSD-RNN as hybrid models. As a result, CSD-RNN outperforms both other models in terms of MSE, MAPE, RMSE and D stat. The findings are useful for policy makers, investors and portfolio managers to forecast the energy trends, and hedge the portfolio risk accordingly. [ABSTRACT FROM AUTHOR]

In the present study, an improved adaptive neuro fuzzy inference system (ANFIS) and multilayer perceptron (MLP) models are hybridized with a sunflower optimization (SO) algorithm and are introduced for lake water level simulation. The Urmia Lake water level is predicted and assessed using the potential of the proposed advanced artificial intelligence (AI) models. The sunflower optimization algorithm is implemented to find the optimal tuning parameters. The results indicated that the ANFIS-SO model with the combination of three lags of rainfall and temperature as input attributes attained the best predictability performance. The minimal values of the root mean square error were RMSE = 1.89 m and 1.92 m for the training and testing modeling phases, respectively. The worst prediction capacity was attained for the long lead (i.e., six months rainfall lag times). The uncertainty analysis showed that the ANFIS-SO model had less uncertainty based on the percentage of more responses in the confidence band and lower bandwidth. Also, different scenarios of water harvesting were investigated with the consideration of environmental restrictions and fair water allocation to stakeholders. Further, studying Urmia Lake water harvesting scenarios displayed that the 30% water harvesting scenario of the lake water improves the lake's water level. [ABSTRACT FROM AUTHOR]

Background and Objective: Obstructive Sleep Apnea is a disease that causes respiratory arrest in sleep and reduces sleep quality. The diagnosis of the disease is made by the physician in two stages by examining the patient records taken with the polysomnography device. Because of the negative aspects of this process, new diagnostic processes and devices are needed. In this article, a new approach to sleep staging, which is one of the diagnostic steps of the disease, was proposed. An artificial intelligence‐based sleep/awake system detection was developed for sleep staging processing. Photoplethysmography (PPG) signal and heart rate variable (HRV) were used in the study. PPG records taken from patient and control groups were cleaned by the digital filter. The HRV parameter was then derived from the PPG signal. Then, 40 features from HRV signal and 46 features from PPG signal were extracted. The extracted features were classified by reduced machine learning techniques with F‐score feature selection method. In order to evaluate the performances of the classifiers, the sensitivity and specificity values, the accuracy rates for each class were computed in the test set and receiver operating characteristic curve prepared. In addition, area under the curve (AUC), Kappa coefficient and F‐score were calculated. According to the results obtained, the system can be realised with 91.09% accuracy rate using 11 PPG and HRV and with 90.01% accuracy rate using 14 HRV features. These success rates are quite enough for the system to work. When all these values are taken into consideration, it is possible to realise a practical sleep/awake detection system. This article suggests that the PPG signal can be used to diagnose obstructive sleep apnea by processing with artificial intelligence and signal processing techniques. [ABSTRACT FROM AUTHOR]

• This work develops a cloud forecasting system for household energy consumption. • The system integrates a hybrid AI model to improve its daily prediction. • The system characterizes energy usage pattern and predicts energy demand. • Identifying anomalous energy consumption in a home in real time. • Residents can proactively reduce the energy consumption of home appliances. In recent years, energy information systems have had an important role in the operational optimization of intelligent buildings to provide such benefits as high efficiency, energy savings and smart services. Interest in the intelligent management of home energy consumption using data mining and time series analysis is increasing. Therefore, this work develops an efficient web-based energy information management system for the power consumption of home appliances that monitors the energy load of a home, analyzes its energy consumption based on machine learning, and then sends information to various stakeholders. It interacts with the end-user through energy dashboards and emails. The web-based system includes a novel hybrid artificial intelligence model to improve its prediction of energy usage. An automatic warning function is also developed to identify anomalous energy consumption in a home in real time. The cloud system automatically sends a message to the user's email whenever a warning is necessary. End-users of this system can use forecast information and anomalous data to enhance the efficiency of energy usage in their buildings especially during peak times by adjusting the operating schedule of their appliances and electrical equipment. [ABSTRACT FROM AUTHOR]

Determining the shear strength of soil is an important task in the design phase of construction project. This study puts forward an artificial intelligence (AI) solution to estimate this parameter of soil. The proposed approach is a hybrid AI model that integrates the least squares support vector machine (LSSVM) and the cuckoo search optimization (CSO). A dataset of 332 soil samples collected from the Trung Luong National Expressway Project in Viet Nam have been used for constructing and validating the AI model. The sample depth, sand percentage, loam percentage, clay percentage, moisture content, wet density of soil, specific gravity, liquid limit, plastic limit, plastic index, and liquid index are used as input variables to predict the output variable of shear strength. In the hybrid AI framework, LSSVM is employed to generalize the functional mapping that estimates the shear strength from the information provided by the aforementioned input variables. Since the model establishment of LSSVM requires a proper setting of the regularization and the kernel function parameters, the CSO algorithm is utilized to automatically determine these parameters. Experimental results show that the prediction accuracy of the hybrid method of LSSVM and CSO (RMSE = 0.082, MAPE = 14.841, and R2 = 0.885) is better than those of the benchmark approaches including the standard LSSVM, the artificial neural network, and the regression tree. Therefore, the proposed method is a promising alternative for assisting construction engineers in the task of soil shear strength estimation. [ABSTRACT FROM AUTHOR]

• Artificial intelligence methods are fast, low cost with high accuracy in predicting the properties of materials. • Investigating the ability of hybrid model of radial basis function neural network with ant colony optimization algorithm for predicting the compressive strength of geopolymer concrete. • Comparing the performance of three various developed artificial intelligence methods for predicting the compressive strength of geopolymer concrete. Geopolymer concrete is a kind of eco-friendly concrete and its important characteristic is that the cement is completely or partially removed from its mixture and other materials such as industrial waste have replaced it. Using industrial waste materials, in particular fly ash, as full or partial replacement of cement in this type of concrete can provide advantages like improving concrete's fresh and hardened traits, decreasing the amounts of released waste materials in the environment, reducing CO 2 footprint and alleviate the pressure on natural resources. According to the acceptable performance of Artificial Intelligence (AI) methods in the various fields, as well as in the issues related to the properties of cementitious materials, in this research three developed AI methods including radial basis function neural network (RBFNN) aided by ant colony optimization algorithm (ACO), group method of data handling (GMDH), and artificial neural network (ANN) was proposed for estimating the compressive strength (that is a notable mechanical character of every type of concrete) of fly ash-based geopolymer concrete (FAGC). To achieve this goal, the information from 360 samples of FAGC was collected from the previous studies. Models' accuracy and predictive capacity have been appraised via Statistical formulas as well as comparing models' outputs with experimental test results. The assessment showed that the performance of all three models for forecasting this mechanical feature of FAGC is acceptable but the RBFNN has the best performance among these proposed models. [ABSTRACT FROM AUTHOR]

Various computational intelligence techniques have been used in the prediction of petroleum reservoir properties. However, each of them has its limitations depending on different conditions such as data size and dimensionality. Hybrid computational intelligence has been introduced as a new paradigm to complement the weaknesses of one technique with the strengths of another or others. This paper presents a computational intelligence hybrid model to overcome some of the limitations of the standalone type-2 fuzzy logic system (T2FLS) model by using a least-square-fitting-based model selection algorithm to reduce the dimensionality of the input data while selecting the best variables. This novel feature selection procedure resulted in the improvement of the performance of T2FLS whose complexity is usually increased and performance degraded with increased dimensionality of input data. The iterative least-square-fitting algorithm part of functional networks (FN) and T2FLS techniques were combined in a hybrid manner to predict the porosity and permeability of North American and Middle Eastern oil and gas reservoirs. Training and testing the T2FLS block of the hybrid model with the best and dimensionally reduced input variables caused the hybrid model to perform better with higher correlation coefficients, lower root mean square errors, and less execution times than the standalone T2FLS model. This work has demonstrated the promising capability of hybrid modelling and has given more insight into the possibility of more robust hybrid models with better functionality and capability indices. [ABSTRACT FROM AUTHOR]

Abstract: Accurately predicting fabricating cost in a timely manner can enhance corporate competitiveness. This study employs the Evolutionary Support Vector Machine Inference Model (ESIM) to predict the cost of manufacturing thin-film transistor liquid–crystal display (TFT-LCD) equipment. The ESIM is a hybrid model integrating a support vector machine (SVM) with a fast messy genetic algorithm (fmGA). The SVM concerns primarily with learning and curve fitting, while the fmGA is focuses on optimization of minimal errors. Recently completed equipment development projects are utilized to assess prediction performance. The ESIM is developed to achieve the fittest C and γ parameters with minimized prediction error when used for cost estimate during conceptual stages. This study describes an actionable knowledge-discovery process using real-world data for high-tech equipment manufacturing industries. Analytical results demonstrate that the ESIM can predict the costs of manufacturing TFT-LCD fabrication equipment with sufficient accuracy. [Copyright &y& Elsevier]

A fully automated and accurate assay of rare cell phenotypes in densely-packed fluorescently-labeled liquid biopsy images remains elusive. Methods: Employing a hybrid artificial intelligence (AI) paradigm that combines traditional rule-based morphological manipulations with modern statistical machine learning, we deployed a next generation software, ALICE (Automated Liquid Biopsy Cell Enumerator) to identify and enumerate minute amounts of tumor cell phenotypes bestrewed in massive populations of leukocytes. As a code designed for futurity, ALICE is armed with internet of things (IOT) connectivity to promote pedagogy and continuing education and also, an advanced cybersecurity system to safeguard against digital attacks from malicious data tampering. Results: By combining robust principal component analysis, random forest classifier and cubic support vector machine, ALICE was able to detect synthetic, anomalous and tampered input images with an average recall and precision of 0.840 and 0.752, respectively. In terms of phenotyping enumeration, ALICE was able to enumerate various circulating tumor cell (CTC) phenotypes with a reliability ranging from 0.725 (substantial agreement) to 0.961 (almost perfect) as compared to human analysts. Further, two subpopulations of circulating hybrid cells (CHCs) were serendipitously discovered and labeled as CHC-1 (DAPI+/CD45+/E-cadherin+/vimentin-) and CHC-2 (DAPI+ /CD45+/E-cadherin+/vimentin+) in the peripheral blood of pancreatic cancer patients. CHC-1 was found to correlate with nodal staging and was able to classify lymph node metastasis with a sensitivity of 0.615 (95% CI: 0.374-0.898) and specificity of 1.000 (95% CI: 1.000-1.000). Conclusion: This study presented a machine-learning-augmented rule-based hybrid AI algorithm with enhanced cybersecurity and connectivity for the automatic and flexibly-adapting enumeration of cellular liquid biopsies. ALICE has the potential to be used in a clinical setting for an accurate and reliable enumeration of CTC phenotypes., Competing Interests: Competing Interests: The authors have declared that no competing interest exists., (© The author(s).)