A survey on evolutionary machine learning

A Multimorbidity Analysis of Hospitalized Patients With COVID-19 in Northwest Italy: Longitudinal Study Using Evolutionary Machine Learning and Health Administrative Data

BACKGROUND

Multimorbidity is a significant public health concern, characterized by the coexistence and interaction of multiple preexisting medical conditions. This complex condition has been associated with an increased risk of COVID-19. Individuals with multimorbidity who contract COVID-19 often face a significant reduction in life expectancy. The postpandemic period has also highlighted an increase in frailty, emphasizing the importance of integrating existing multimorbidity details into epidemiological risk assessments. Managing clinical data that include medical histories presents significant challenges, particularly due to the sparsity of data arising from the rarity of multimorbidity conditions. Also, the complex enumeration of combinatorial multimorbidity features introduces challenges associated with combinatorial explosions.

OBJECTIVE

This study aims to assess the severity of COVID-19 in individuals with multiple medical conditions, considering their demographic characteristics such as age and sex. We propose an evolutionary machine learning model designed to handle sparsity, analyzing preexisting multimorbidity profiles of patients hospitalized with COVID-19 based on their medical history. Our objective is to identify the optimal set of multimorbidity feature combinations strongly associated with COVID-19 severity. We also apply the Apriori algorithm to these evolutionarily derived predictive feature combinations to identify those with high support.

METHODS

We used data from 3 administrative sources in Piedmont, Italy, involving 12,793 individuals aged 45-74 years who tested positive for COVID-19 between February and May 2020. From their 5-year pre-COVID-19 medical histories, we extracted multimorbidity features, including drug prescriptions, disease diagnoses, sex, and age. Focusing on COVID-19 hospitalization, we segmented the data into 4 cohorts based on age and sex. Addressing data imbalance through random resampling, we compared various machine learning algorithms to identify the optimal classification model for our evolutionary approach. Using 5-fold cross-validation, we evaluated each model's performance. Our evolutionary algorithm, utilizing a deep learning classifier, generated prediction-based fitness scores to pinpoint multimorbidity combinations associated with COVID-19 hospitalization risk. Eventually, the Apriori algorithm was applied to identify frequent combinations with high support.

RESULTS

We identified multimorbidity predictors associated with COVID-19 hospitalization, indicating more severe COVID-19 outcomes. Frequently occurring morbidity features in the final evolved combinations were age>53, R03BA (glucocorticoid inhalants), and N03AX (other antiepileptics) in cohort 1; A10BA (biguanide or metformin) and N02BE (anilides) in cohort 2; N02AX (other opioids) and M04AA (preparations inhibiting uric acid production) in cohort 3; and G04CA (Alpha-adrenoreceptor antagonists) in cohort 4.

CONCLUSIONS

When combined with other multimorbidity features, even less prevalent medical conditions show associations with the outcome. This study provides insights beyond COVID-19, demonstrating how repurposed administrative data can be adapted and contribute to enhanced risk assessment for vulnerable populations.

Smarter eco-cities and their leading-edge artificial intelligence of things solutions for environmental sustainability: A comprehensive systematic review

The recent advancements made in the realms of Artificial Intelligence (AI) and Artificial Intelligence of Things (AIoT) have unveiled transformative prospects and opportunities to enhance and optimize the environmental performance and efficiency of smart cities. These strides have, in turn, impacted smart eco-cities, catalyzing ongoing improvements and driving solutions to address complex environmental challenges. This aligns with the visionary concept of smarter eco-cities, an emerging paradigm of urbanism characterized by the seamless integration of advanced technologies and environmental strategies. However, there remains a significant gap in thoroughly understanding this new paradigm and the intricate spectrum of its multifaceted underlying dimensions. To bridge this gap, this study provides a comprehensive systematic review of the burgeoning landscape of smarter eco-cities and their leading-edge AI and AIoT solutions for environmental sustainability. To ensure thoroughness, the study employs a unified evidence synthesis framework integrating aggregative, configurative, and narrative synthesis approaches. At the core of this study lie these subsequent research inquiries: What are the foundational underpinnings of emerging smarter eco-cities, and how do they intricately interrelate, particularly urbanism paradigms, environmental solutions, and data-driven technologies? What are the key drivers and enablers propelling the materialization of smarter eco-cities? What are the primary AI and AIoT solutions that can be harnessed in the development of smarter eco-cities? In what ways do AI and AIoT technologies contribute to fostering environmental sustainability practices, and what potential benefits and opportunities do they offer for smarter eco-cities? What challenges and barriers arise in the implementation of AI and AIoT solutions for the development of smarter eco-cities? The findings significantly deepen and broaden our understanding of both the significant potential of AI and AIoT technologies to enhance sustainable urban development practices, as well as the formidable nature of the challenges they pose. Beyond theoretical enrichment, these findings offer invaluable insights and new perspectives poised to empower policymakers, practitioners, and researchers to advance the integration of eco-urbanism and AI- and AIoT-driven urbanism. Through an insightful exploration of the contemporary urban landscape and the identification of successfully applied AI and AIoT solutions, stakeholders gain the necessary groundwork for making well-informed decisions, implementing effective strategies, and designing policies that prioritize environmental well-being.

Modeling crude oil pyrolysis process using advanced white-box and black-box machine learning techniques

Accurate prediction of fuel deposition during crude oil pyrolysis is pivotal for sustaining the combustion front and ensuring the effectiveness of in-situ combustion enhanced oil recovery (ISC EOR). Employing 2071 experimental TGA datasets from 13 diverse crude oil samples extracted from the literature, this study sought to precisely model crude oil pyrolysis. A suite of robust machine learning techniques, encompassing three black-box approaches (Categorical Gradient Boosting-CatBoost, Gaussian Process Regression-GPR, Extreme Gradient Boosting-XGBoost), and a white-box approach (Genetic Programming-GP), was employed to estimate crude oil residue at varying temperature intervals during TGA runs. Notably, the XGBoost model emerged as the most accurate, boasting a mean absolute percentage error (MAPE) of 0.7796% and a determination coefficient (R2) of 0.9999. Subsequently, the GPR, CatBoost, and GP models demonstrated commendable performance. The GP model, while displaying slightly higher error in comparison to the black-box models, yielded acceptable results and proved suitable for swift estimation of crude oil residue during pyrolysis. Furthermore, a sensitivity analysis was conducted to reveal the varying influence of input parameters on residual crude oil during pyrolysis. Among the inputs, temperature and asphaltenes were identified as the most influential factors in the crude oil pyrolysis process. Higher temperatures and oil °API gravity were associated with a negative impact, leading to a decrease in fuel deposition. On the other hand, increased values of asphaltenes, resins, and heating rates showed a positive impact, resulting in an increase in fuel deposition. These findings underscore the importance of precise modeling for fuel deposition during crude oil pyrolysis, offering insights that can significantly benefit ISC EOR practices.

Multitask Feature Learning as Multiobjective Optimization: A New Genetic Programming Approach to Image Classification

Feature learning is a promising approach to image classification. However, it is difficult due to high image variations. When the training data are small, it becomes even more challenging, due to the risk of overfitting. Multitask feature learning has shown the potential for improving generalization. However, existing methods are not effective for handling the case that multiple tasks are partially conflicting. Therefore, for the first time, this article proposes to solve a multitask feature learning problem as a multiobjective optimization problem by developing a genetic programming approach with a new representation to image classification. In the new approach, all the tasks share the same solution space and each solution is evaluated on multiple tasks so that the objectives of all the tasks can be optimized simultaneously using a single population. To learn effective features, a new and compact program representation is developed to allow the new approach to evolving solutions shared across tasks. The new approach can automatically find a diverse set of nondominated solutions that achieve good tradeoffs between different tasks. To further reduce the risk of overfitting, an ensemble is created by selecting nondominated solutions to solve each image classification task. The results show that the new approach significantly outperforms a large number of benchmark methods on six problems consisting of 15 image classification datasets of varying difficulty. Further analysis shows that these new designs are effective for improving the performance. The detailed analysis clearly reveals the benefits of solving multitask feature learning as multiobjective optimization in improving the generalization.

Automatically Diagnosing Skin Cancers From Multimodality Images Using Two-Stage Genetic Programming

Developing a computer-aided diagnostic system for detecting various skin malignancies from images has attracted many researchers. Unlike many machine-learning approaches, such as artificial neural networks, genetic programming (GP) automatically evolves models with flexible representation. GP successfully provides effective solutions using its intrinsic ability to select prominent features (i.e., feature selection) and build new features (i.e., feature construction). Existing approaches have utilized GP to construct new features from the complete set of original features and the set of operators. However, the complete set of features may contain redundant or irrelevant features that do not provide useful information for classification. This study aims to develop a two-stage GP method, where the first stage selects prominent features, and the second stage constructs new features from these selected features and operators, such as multiplication in a wrapper approach to improve the classification performance. To include local, global, texture, color, and multiscale image properties of skin images, GP selects and constructs features extracted from local binary patterns and pyramid-structured wavelet decomposition. The accuracy of this GP method is assessed using two real-world skin image datasets captured from the standard camera and specialized instruments, and compared with commonly used classification algorithms, three state of the art, and an existing embedded GP method. The results reveal that this new approach of feature selection and feature construction effectively helps improve the performance of the machine-learning classification algorithms. Unlike other black-box models, the evolved models by GP are interpretable; therefore, the proposed method can assist dermatologists to identify prominent features, which has been shown by further analysis on the evolved models.

Machine Learning Diffuse Optical Tomography Using Extreme Gradient Boosting and Genetic Programming

Diffuse optical tomography (DOT) is a non-invasive method for detecting breast cancer; however, it struggles to produce high-quality images due to the complexity of scattered light and the limitations of traditional image reconstruction algorithms. These algorithms can be affected by boundary conditions and have a low imaging accuracy, a shallow imaging depth, a long computation time, and a high signal-to-noise ratio. However, machine learning can potentially improve the performance of DOT by being better equipped to solve inverse problems, perform regression, classify medical images, and reconstruct biomedical images. In this study, we utilized a machine learning model called "XGBoost" to detect tumors in inhomogeneous breasts and applied a post-processing technique based on genetic programming to improve accuracy. The proposed algorithm was tested using simulated DOT measurements from complex inhomogeneous breasts and evaluated using the cosine similarity metrics and root mean square error loss. The results showed that the use of XGBoost and genetic programming in DOT could lead to more accurate and non-invasive detection of tumors in inhomogeneous breasts compared to traditional methods, with the reconstructed breasts having an average cosine similarity of more than 0.97 ± 0.07 and average root mean square error of around 0.1270 ± 0.0031 compared to the ground truth.

GENECI: A novel evolutionary machine learning consensus-based approach for the inference of gene regulatory networks

Gene regulatory networks define the interactions between DNA products and other substances in cells. Increasing knowledge of these networks improves the level of detail with which the processes that trigger different diseases are described and fosters the development of new therapeutic targets. These networks are usually represented by graphs, and the primary sources for their correct construction are usually time series from differential expression data. The inference of networks from this data type has been approached differently in the literature. Mostly, computational learning techniques have been implemented, which have finally shown some specialization in specific datasets. For this reason, the need arises to create new and more robust strategies for reaching a consensus based on previous results to gain a particular capacity for generalization. This paper presents GENECI (GEne NEtwork Consensus Inference), an evolutionary machine learning approach that acts as an organizer for constructing ensembles to process the results of the main inference techniques reported in the literature and to optimize the consensus network derived from them, according to their confidence levels and topological characteristics. After its design, the proposal was confronted with datasets collected from academic benchmarks (DREAM challenges and IRMA network) to quantify its accuracy. Subsequently, it was applied to a real-world biological network of melanoma patients whose results could be contrasted with medical research collected in the literature. Finally, it has been proved that its ability to optimize the consensus of several networks leads to outstanding robustness and accuracy, gaining a certain generalization capacity after facing the inference of multiple datasets. The source code is hosted in a public repository at GitHub under MIT license: https://github.com/AdrianSeguraOrtiz/GENECI. Moreover, to facilitate its installation and use, the software associated with this implementation has been encapsulated in a python package available at PyPI: https://pypi.org/project/geneci/.

Instance Selection-Based Surrogate-Assisted Genetic Programming for Feature Learning in Image Classification

Genetic programming (GP) has been applied to feature learning for image classification and achieved promising results. However, many GP-based feature learning algorithms are computationally expensive due to a large number of expensive fitness evaluations, especially when using a large number of training instances/images. Instance selection aims to select a small subset of training instances, which can reduce the computational cost. Surrogate-assisted evolutionary algorithms often replace expensive fitness evaluations by building surrogate models. This article proposes an instance selection-based surrogate-assisted GP for fast feature learning in image classification. The instance selection method selects multiple small subsets of images from the original training set to form surrogate training sets of different sizes. The proposed approach gradually uses these surrogate training sets to reduce the overall computational cost using a static or dynamic strategy. At each generation, the proposed approach evaluates the entire population on the small surrogate training sets and only evaluates ten current best individuals on the entire training set. The features learned by the proposed approach are fed into linear support vector machines for classification. Extensive experiments show that the proposed approach can not only significantly reduce the computational cost but also improve the generalisation performance over the baseline method, which uses the entire training set for fitness evaluations, on 11 different image datasets. The comparisons with other state-of-the-art GP and non-GP methods further demonstrate the effectiveness of the proposed approach. Further analysis shows that using multiple surrogate training sets in the proposed approach achieves better performance than using a single surrogate training set and using a random instance selection method.

Mobile Phone Data: A Survey of Techniques, Features, and Applications

Due to the rapid growth in the use of smartphones, the digital traces (e.g., mobile phone data, call detail records) left by the use of these devices have been widely employed to assess and predict human communication behaviors and mobility patterns in various disciplines and domains, such as urban sensing, epidemiology, public transportation, data protection, and criminology. These digital traces provide significant spatiotemporal (geospatial and time-related) data, revealing people's mobility patterns as well as communication (incoming and outgoing calls) data, revealing people's social networks and interactions. Thus, service providers collect smartphone data by recording the details of every user activity or interaction (e.g., making a phone call, sending a text message, or accessing the internet) done using a smartphone and storing these details on their databases. This paper surveys different methods and approaches for assessing and predicting human communication behaviors and mobility patterns from mobile phone data and differentiates them in terms of their strengths and weaknesses. It also gives information about spatial, temporal, and call characteristics that have been extracted from mobile phone data and used to model how people communicate and move. We survey mobile phone data research published between 2013 and 2021 from eight main databases, namely, the ACM Digital Library, IEEE Xplore, MDPI, SAGE, Science Direct, Scopus, SpringerLink, and Web of Science. Based on our inclusion and exclusion criteria, 148 studies were selected.

Use of industry 4.0 technologies to reduce and valorize seafood waste and by-products: A narrative review on current knowledge

Fish and other seafood products represent a valuable source of many nutrients and micronutrients for the human diet and contribute significantly to global food security. However, considerable amounts of seafood waste and by-products are generated along the seafood value and supply chain, from the sea to the consumer table, causing severe environmental damage and significant economic loss. Therefore, innovative solutions and alternative approaches are urgently needed to ensure a better management of seafood discards and mitigate their economic and environmental burdens. The use of emerging technologies, including the fourth industrial revolution (Industry 4.0) innovations (such as Artificial Intelligence, Big Data, smart sensors, and the Internet of Things, and other advanced technologies) to reduce and valorize seafood waste and by-products could be a promising strategy to enhance blue economy and food sustainability around the globe. This narrative review focuses on the issues and risks associated with the underutilization of waste and by-products resulting from fisheries and other seafood industries. Particularly, recent technological advances and digital tools being harnessed for the prevention and valorization of these natural invaluable resources are highlighted.

Applications of deep learning into supply chain management: a systematic literature review and a framework for future research

In today’s complex and ever-changing world, Supply Chain Management (SCM) is increasingly becoming a cornerstone to any company to reckon with in this global era for all industries. The rapidly growing interest in the application of Deep Learning (a class of machine learning algorithms) in SCM, has urged the need for an up-to-date systematic review on the research development. The main purpose of this study is to provide a comprehensive vision by reviewing a set of 43 papers about applications of Deep Learning (DL) methods to the SCM, as well as the trends, perspectives, and potential research gaps. This review uses content analysis to answer three research questions namely: 1- What SCM problems have been solved by the use of DL techniques? 2- What DL algorithms have been used to solve these problems? 3- What alternative algorithms have been used to tackle the same problems? And do DL outperform these methods and through which evaluation metrics? This review also responds to this call by developing a conceptual framework in a value-adding perspective that provides a full picture of areas on where and how DL can be applied within the SCM context. This makes it easier to identify potential applications to corporations, in addition to potential future research areas to science. It might also provide businesses a competitive advantage over their competitors by allowing them to add value to their data by analyzing it quickly and precisely.

Genetic Programming-Based Discriminative Feature Learning for Low-Quality Image Classification

Being able to learn discriminative features from low-quality images has raised much attention recently due to their wide applications ranging from autonomous driving to safety surveillance. However, this task is difficult due to high variations across images, such as scale, rotation, illumination, and viewpoint, and distortions in images, such as blur, low contrast, and noise. Image preprocessing could improve the quality of the images, but it often requires human intervention and domain knowledge. Genetic programming (GP) with a flexible representation can automatically perform image preprocessing and feature extraction without human intervention. Therefore, this study proposes a new evolutionary learning approach using GP (EFLGP) to learn discriminative features from images with blur, low contrast, and noise for classification. In the proposed approach, we develop a new program structure (individual representation), a new function set, and a new terminal set. With these new designs, EFLGP can detect small regions from a large input low-quality image, select image operators to process the regions or detect features from the small regions, and output a flexible number of discriminative features. A set of commonly used image preprocessing operators is employed as functions in EFLGP to allow it to search for solutions that can effectively handle low-quality image data. The performance of EFLGP is comprehensively investigated on eight datasets of varying difficulty under the original (clean), blur, low contrast, and noise scenarios, and compared with a large number of benchmark methods using handcrafted features and deep features. The experimental results show that EFLGP achieves significantly better or similar results in most comparisons. The results also reveal that EFLGP is more invariant than the benchmark methods to blur, low contrast, and noise.

A hybrid metaheuristic-deep learning technique for the pan-classification of cancer based on DNA methylation

Background

DNA Methylation is one of the most important epigenetic processes that are crucial to regulating the functioning of the human genome without altering the DNA sequence. DNA Methylation data for cancer patients are becoming more accessible than ever, which is attributed to newer DNA sequencing technologies, notably, the relatively low-cost DNA microarray technology by Illumina Infinium. This technology makes it possible to study DNA methylation at hundreds of thousands of different loci. Currently, most of the research found in the literature focuses on the discovery of DNA methylation markers for specific cancer types. A relatively small number of studies have attempted to find unified DNA methylation biomarkers that can diagnose different types of cancer (pan-cancer classification).

Results

In this study, the aim is to conduct a pan-classification of cancer disease. We retrieved individual data for different types of cancer patients from The Cancer Genome Atlas (TCGA) portal. We selected data for many cancer types: Breast Cancer (BRCA), Ovary Cancer (OV), Stomach Cancer (STOMACH), Colon Cancer (COAD), Kidney Cancer (KIRC), Liver Cancer (LIHC), Lung Cancer (LUSC), Prostate Cancer (PRAD) and Thyroid cancer (THCA). The data was pre-processed and later used to build the required dataset. The system that we developed consists of two main stages. The purpose of the first stage is to perform feature selection and, therefore, decrease the dimensionality of the DNA methylation loci (features). This is accomplished using an unsupervised metaheuristic technique. As for the second stage, we used supervised machine learning and developed deep neural network (DNN) models to help classify the samples’ malignancy status and cancer type. Experimental results showed that compared to recently published methods, our proposed system achieved better classification results in terms of recall, and similar and higher results in terms of precision and accuracy. The proposed system also achieved an excellent receiver operating characteristic area under the curve (ROC AUC) values varying from 0.85 to 0.89.

Conclusions

This research presented an effective new approach to classify different cancer types based on DNA methylation data retrieved from TCGA. The performance of the proposed system was compared to recently published works, using different performance metrics. It provided better results, confirming the effectiveness of the proposed method for classifying different cancer types based on DNA methylation data.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04815-7.

Recent Trends in AI-Based Intelligent Sensing

In recent years, intelligent sensing has gained significant attention because of its autonomous decision-making ability to solve complex problems. Today, smart sensors complement and enhance the capabilities of human beings and have been widely embraced in numerous application areas. Artificial intelligence (AI) has made astounding growth in domains of natural language processing, machine learning (ML), and computer vision. The methods based on AI enable a computer to learn and monitor activities by sensing the source of information in a real-time environment. The combination of these two technologies provides a promising solution in intelligent sensing. This survey provides a comprehensive summary of recent research on AI-based algorithms for intelligent sensing. This work also presents a comparative analysis of algorithms, models, influential parameters, available datasets, applications and projects in the area of intelligent sensing. Furthermore, we present a taxonomy of AI models along with the cutting edge approaches. Finally, we highlight challenges and open issues, followed by the future research directions pertaining to this exciting and fast-moving field.

Crossover based technique for data augmentation

BACKGROUND AND OBJECTIVE

Medical image classification problems are frequently constrained by the availability of datasets. "Data augmentation" has come as a data enhancement and data enrichment solution to the challenge of limited data. Traditionally data augmentation techniques are based on linear and label preserving transformations; however, recent works have demonstrated that even non-linear, non-label preserving techniques can be unexpectedly effective. This paper proposes a non-linear data augmentation technique for the medical domain and explores its results.

METHODS

This paper introduces "Crossover technique", a new data augmentation technique for Convolutional Neural Networks in Medical Image Classification problems. Our technique synthesizes a pair of samples by applying two-point crossover on the already available training dataset. By this technique, we create N new samples from N training samples. The proposed crossover based data augmentation technique, although non-label preserving, has performed significantly better in terms of increased accuracy and reduced loss for all the tested datasets over varied architectures.

RESULTS

The proposed method was tested on three publicly available medical datasets with various network architectures. For the mini-MIAS database of mammograms, our method improved the accuracy by 1.47%, achieving 80.15% using VGG-16 architecture. Our method works fine for both gray-scale as well as RGB images, as on the PH2 database for Skin Cancer, it improved the accuracy by 3.57%, achieving 85.71% using VGG-19 architecture. In addition, our technique improved accuracy on the brain tumor dataset by 0.40%, achieving 97.97% using VGG-16 architecture.

CONCLUSION

The proposed novel crossover technique for training the Convolutional Neural Network (CNN) is painless to implement by applying two-point crossover on two images to form new images. The method would go a long way in tackling the challenges of limited datasets and problems of class imbalances in medical image analysis. Our code is available at https://github.com/rishiraj-cs/Crossover-augmentation.

Rademacher Complexity for Enhancing the Generalization of Genetic Programming for Symbolic Regression

Model complexity has a close relationship with the generalization ability and the interpretability of the learned models. Simple models are more likely to generalize well and easy to interpret. However, too much emphasis on minimizing complexity can prevent the discovery of more complex yet more accurate solutions. Genetic programming (GP) has a trend of generating overcomplex models that are difficult to interpret while not being able to generalize well. This work proposes a novel complexity measure based on the Rademacher complexity for GP for symbolic regression. The complexity of an evolved model is measured by the maximum correlation between the model and the Rademacher variables on the selected training instances. Taking minimizing the training error and the Rademacher complexity of the models as the two objectives, the proposed GP method has shown to be much superior to the standard GP on generalization performance. Compared with GP equipped with two state-of-the-art complexity measures, the proposed method still has a notable advance on generating a better front consisting of individuals with lower generalization errors and being simpler in the behavioral complexity. Further analyses reveal that compared with the state-of-the-art methods, the proposed GP method evolves models that are much closer to the target models in the model structure, and have better interpretability.

Many-Body Neural Network-Based Force Field for Structure-Based Coarse-Graining of Water

High-fidelity results from atomistic simulations can only be obtained by using accurate force-field (FF) parameters. Although empirical FFs are commonly used in the modeling of atomistic systems due to their simplicity, they have many limitations inherent in the crude approximations associated with their analytical form. Recent advances in neural network-based FFs have led to more accurate FFs by using symmetry functions or full many-body expansions. However, this approach leads to several issues including the arbitrariness of the symmetry functions, and the intangible and uninterpretable interactions which are only known once the positions of all atoms are set. More importantly, training is another bottleneck, as high-quality force and energy information is required, which is usually not accessible from experimental data. To solve these issues within the context of structure-based coarse-graining methods, we switch in this work to a local-search method to target the reference structure instead of using conventional backpropagation algorithms used to target the forces and energies of the reference structure. Our FF is decomposed into two-, three-, and higher-order terms, where each term is modeled with a separate neural network. To show the versatility of our method, we study four different systems, namely, Stillinger-Weber particles as an atomistic case and three water models, namely SPC/E, MB-pol, and ab initio, as coarse-graining cases. We show the successful application of our approach, by reproducing structural properties of different water models, followed by providing insight into the role of two-and three-body interactions. The results of all models indicate that the double-well isotropic pair potential, the signature of water-like behavior in an isotropic system, vanishes upon inclusion of the three-body interaction, showing dominance of the three-body interaction over the two-body interaction in water-like behavior with the single-well isotropic pair potential.

An Object-Based Genetic Programming Approach for Cropland Field Extraction

Cropland fields are the basic spatial units for agricultural management, and information about their distribution is critical for analyzing agricultural investments and management. However, the extraction of cropland fields of smallholder farms is a challenging task because of their irregular shapes and diverse spectrum. In this paper, we proposed a new object-based Genetic Programming (GP) approach to extract cropland fields. The proposed approach used the multiresolution segmentation (MRS) method to acquire objects from a very high resolution (VHR) image, and extracted spectral, shape and texture features as inputs for GP. Then GP was used to automatically evolve the optimal classifier to extract cropland fields. The results show that the proposed approach has obtained high accuracy in two areas with different landscape complexities. Further analysis show that the GP approach significantly outperforms five commonly used classifiers, including K-Nearest Neighbor (KNN), Decision Tree (DT), Naïve Bayes (NB), Support Vector Machine (SVM), and Random Forest (RF). By using different numbers of training samples, GP can maintain high accuracy with any volume of samples compared to other classifiers.

High-Dimensional Unbalanced Binary Classification by Genetic Programming with Multi-Criterion Fitness Evaluation and Selection

High-dimensional unbalanced classification is challenging because of the joint effects of high dimensionality and class imbalance. Genetic programming (GP) has the potential benefits for use in high-dimensional classification due to its built-in capability to select informative features. However, once data are not evenly distributed, GP tends to develop biased classifiers which achieve a high accuracy on the majority class but a low accuracy on the minority class. Unfortunately, the minority class is often at least as important as the majority class. It is of importance to investigate how GP can be effectively utilized for high-dimensional unbalanced classification. In this article, to address the performance bias issue of GP, a new two-criterion fitness function is developed, which considers two criteria, that is, the approximation of area under the curve (AUC) and the classification clarity (i.e., how well a program can separate two classes). The obtained values on the two criteria are combined in pairs, instead of summing them together. Furthermore, this article designs a three-criterion tournament selection to effectively identify and select good programs to be used by genetic operators for generating offspring during the evolutionary learning process. The experimental results show that the proposed method achieves better classification performance than other compared methods.

Estimating Boundary Layer Height from LiDAR Data under Complex Atmospheric Conditions Using Machine Learning

Reliable estimation of the atmospheric boundary layer height (ABLH) is critical for a range of meteorological applications, including air quality assessment and weather forecasting. Several algorithms have been proposed to detect ABLH from aerosol LiDAR backscatter data. However, most of these focus on cloud-free conditions or use other ancillary instruments due to strong interference from clouds or residual layer aerosols. In this paper, a machine learning method named the Mahalanobis transform K-near-means (MKnm) algorithm is first proposed to derive ABLH under complex atmospheric conditions using only LiDAR-based instruments. It was applied to the micro pulse LiDAR data obtained at the Southern Great Plains site of the Atmospheric Radiation Measurement (ARM) program. The diurnal cycles of ABLH from cloudy weather were detected by using the gradient method (GM), wavelet covariance transform method (WM), K-means, and MKnm. Meanwhile, the ABLH obtained by these four methods under cloud or residual layer conditions based on micropulse LiDAR data were compared with the reference height retrieved from radiosonde data. The results show that MKnm was good at tracking the diurnal variation of ABLH, and the ABLHs obtained by it have remarkable correlation coefficients and smaller mean absolute error and mean deviation with the radiosonde-derived ABLHs than those measured by other three methods. We conclude that MKnm is a promising algorithm to estimate ABLH under cloud or residual layer conditions.

A survey on providing customer and public administration based services using AI: chatbot

A chatbot is emerged as an effective tool to address the user queries in automated, most appropriate and accurate way. Depending upon the complexity of the subject domain, researchers are employing variety of soft-computing techniques to make the chatbot user-friendly. It is observed that chatbots have flooded the globe with wide range of services including ordering foods, suggesting products, advising for insurance policies, providing customer support, giving financial assistance, schedule meetings etc. However, public administration based services wherein chatbot intervention influence the most, is not explored yet. This paper discuses about artificial intelligence based chatbots including their applications, challenges, architecture and models. It also talks about evolution of chatbots starting from Turing Test and Rule-based chatbots to advanced Artificial Intelligence based Chatbots (AI-Chatbots). AI-Chatbots are providing much kind of services, which this paper outlines into two main aspects including customer based services and public administration based services. The purpose of this survey is to understand and explore the possibility of customer & public administration services based chatbot. The survey demonstrates that there exist an immense potential in the AI assisted chatbot system for providing customer services and providing better governance in public administration services.

Automatic Feature Extraction and Construction Using Genetic Programming for Rotating Machinery Fault Diagnosis

Feature extraction is an essential process in the intelligent fault diagnosis of rotating machinery. Although existing feature extraction methods can obtain representative features from the original signal, domain knowledge and expert experience are often required. In this article, a novel diagnosis approach based on evolutionary learning, namely, automatic feature extraction and construction using genetic programming (AFECGP), is proposed to automatically generate informative and discriminative features from original vibration signals for identifying different fault types of rotating machinery. To achieve this, a new program structure, a new function set, and a new terminal set are developed in AFECGP to allow it to detect important subband signals and extract and construct informative features, automatically and simultaneously. More important, AFECGP can produce a flexible number of features for classification. Having the generated features, k -Nearest Neighbors is employed to perform fault diagnosis. The performance of the AFECGP-based fault diagnosis approach is evaluated on four fault diagnosis datasets of varying difficulty and compared with 14 baseline methods. The results show that the proposed approach achieves better fault diagnosis accuracy on all the datasets than the competitive methods and can effectively identify different fault conditions of rolling bearing, gear, and rotor.

A Digitalized Design Risk Analysis Tool with Machine-Learning Algorithm for EPC Contractor’s Technical Specifications Assessment on Bidding

Engineering, Procurement, and Construction (EPC) projects span the entire cycle of industrial plants, from bidding to engineering, construction, and start-up operation and maintenance. Most EPC contractors do not have systematic decision-making tools when bidding for the project; therefore, they rely on manual analysis and experience in evaluating the bidding contract documents, including technical specifications. Oftentimes, they miss or underestimate the presence of technical risk clauses or risk severity, potentially create with a low bid price and tight construction schedule, and eventually experience severe cost overrun or/and completion delays. Through this study, two digital modules, Technical Risk Extraction and Design Parameter Extraction, were developed to extract and analyze risks in the project’s technical specifications based on machine learning and AI algorithms. In the Technical Risk Extraction module, technical risk keywords in the bidding technical specifications are collected, lexiconized, and then extracted through phrase matcher technology, a machine learning natural language processing technique. The Design Parameter Extraction module compares the collected engineering standards’ so-called standard design parameters and the plant owner’s technical requirements on the bid so that a contractor’s engineers can detect the difference between them and negotiate them. As described above, through the two modules, the risk clauses of the technical specifications of the project are extracted, and the risks are detected and reconsidered in the bidding or execution of the project, thereby minimizing project risk and providing a theoretical foundation and system for contractors. As a result of the pilot test performed to verify the performance and validity of the two modules, the design risk extraction accuracy of the system module has a relative advantage of 50 percent or more, compared to the risk extraction accuracy of manual evaluation by engineers. In addition, the speed of the automatic extraction and analysis of the system modules are 80 times faster than the engineer’s manual analysis time, thereby minimizing project loss due to errors or omissions due to design risk analysis during the project bidding period with a set deadline.

Deep learning in electron microscopy

Deep learning is transforming most areas of science and technology, including electron microscopy. This review paper offers a practical perspective aimed at developers with limited familiarity. For context, we review popular applications of deep learning in electron microscopy. Following, we discuss hardware and software needed to get started with deep learning and interface with electron microscopes. We then review neural network components, popular architectures, and their optimization. Finally, we discuss future directions of deep learning in electron microscopy.