The amount of microplastics (MPs) present in marine ecosystems are a growing concern, with potential impacts on human health because they are associated with an increase in the ecotoxicity of certain foods, such as fish. As a result, there has been a growing interest in developing effective methods for the analysis of MPs in marine waters. Traditional methods for MP analysis involve visual inspection and manual sorting, which can be time-consuming and subject to human error. However, novel methods have been developed that offer more efficient and accurate analyses. One such method is based on spectroscopy, such as Fourier transform infrared spectroscopy (FTIR). Another method involves the use of fluorescent dyes, which can selectively bind to microplastics and allow for their detection under UV light. Additionally, machine learning approaches have been developed to analyze large volumes of water samples for MP detection and classification. These methods involve the use of specialized a... [more]

In this research work, an approach using You Only Look Once version three (YOLOv3)-TensorFlow for abalone detection and Deep Simple Online Real-time Tracking (DeepSORT) for abalone tracking in conveyor belt systems is proposed. The conveyor belt system works in coordination with the cameras used to detect abalones. Considering the computational effectiveness and improved detection algorithms, this proposal is promising compared to the previously proposed methods. Some of these methods have low effectiveness and accuracy, and they provide an incorrect counting rate because some of the abalones tend to entangle, resulting in counting two or more abalones as one. Conducting detection and tracking research is crucial to achieve modern solutions for small- and large-scale fishing industries that enable them to accomplish higher automation, non-invasiveness, and low cost. This study is based on the development and improvement of counting analysis tools for automation in the fishing industry.... [more]

The gastric cancer risk prediction model used for large-scale gastric cancer screening and individual risk stratification is an artificial intelligence tool that combines clinical diagnostic data with a classification algorithm. The ability to automatically make a quantitative assessment of complex clinical data contributes to increased accuracy for diagnosis with higher efficiency, significantly reducing the incidence of advanced gastric cancer. Previous studies have explored the predictive performance of gastric cancer risk prediction models, as well as the predictive factors and algorithms between each model, but have reached controversial conclusions. Thus, the performance of current machine-learning-based gastric cancer risk prediction models alongside the clinical relevance of different predictive factors needs to be evaluated to help build more efficient and feasible models in the future. In this systematic review, we summarize the current research progress related to the gastri... [more]

This paper presents a machine learning (ML) approach to predict the potential health issues of solvents by uncovering the hidden relationship between substances and toxicity. Solvent selection is a crucial step in industrial processes. However, prolonged exposure to solvents has been found to pose significant risks to human health. To mitigate these hazards, it is crucial to develop a predictive model for health performance by identifying the contributing factors to solvent toxicity. This research aims to develop a predictive model for health issues related to solvent toxicity. Among various algorithms in ML, Rough Set Machine Learning (RSML) was chosen for this work due to its interpretable nature of the generated models. The models have been developed through data collection on the toxicity of various organic solvents, the construction of predictive models with decision rules, and model verification. The results reveal correlations between solvent toxicity and the Balaban index, vale... [more]

Machine learning is the main technical means for lithofacies logging identification. As the main target of shale oil spatial distribution prediction, mud shale petrography is subjected to the constraints of stratigraphic inhomogeneity and logging information redundancy. Therefore, choosing the most applicable machine learning method for different geological characteristics and data situations is one of the key aspects of high-precision lithofacies identification. However, only a few studies have been conducted on the applicability of machine learning methods for mud shale petrography. This paper aims to identify lithofacies using commonly used machine learning methods. The study employs five supervised learning algorithms, namely Random Forest Algorithm (RF), BP Neural Network Algorithm (BPANN), Gradient Boosting Decision Tree Method (GBDT), Nearest Neighbor Method (KNN), and Vector Machine Method (SVM), as well as four unsupervised learning algorithms, namely K-means, DBSCAN, SOM, and... [more]

Blends of bitumen, clay, and quartz in water are obtained from the surface mining of the Athabasca Oil Sands. To facilitate its transportation through pipelines, this mixture is usually diluted with locally produced naphtha. As a result of this, naphtha has to be recovered later, in a naphtha recovery unit (NRU). The NRU process is a complex one and requires the knowledge of Vapour-Liquid-Liquid Equilibrium (VLLE) thermodynamics. The present study uses experimental data, obtained in a CREC-VL-Cell, and Artificial Intelligence (AI) for vapour-liquid-liquid equilibrium (VLLE) calculations. The proposed Artificial Neural Networks (ANNs) do not require prior knowledge of the number of vapour-liquid phases. These ANNs involve hyperparameters that are used to obtain the best ANN model architecture. To accomplish this, this study considers (a) R2 Coefficients of Determination and (b) ANN training requirements to avoid data underfitting and overfitting. Results demonstrate that temperature has... [more]

Sugarcane is one of the main agro-industrial products consumed worldwide, and, therefore, the use of suitable soils is a key factor to maximize its production. As a result, the need to evaluate soil matrices, including many physical, chemical, and biological parameters, to determine the soil’s aptitude for growing food crops increases. Machine learning techniques were used to perform an in-depth analysis of the physicochemical indicators of vertisol-type soils used in sugarcane production. The importance of the relationship between each of the indicators was studied. Furthermore, and the main objective of the present work, was the determination of the minimum number of the most important physicochemical indicators necessary to evaluate the agricultural suitability of the soils, with a view to reducing the number of analyses in terms of physicochemical indicators required for the evaluation. The results obtained relating to the estimation of agricultural capability using different numbe... [more]

This article aims to enhance technological advancements in the classification of polyethylene terephthalate (PET) bottle plastic, positively impacting sustainable development and providing effective solutions for collection centers (CC) in Mexico. Three experimental designs and machine learning tools for data processing were developed. The experiments considered three factors: bottle size, liquid volume, and bottle labels. The first experiment focused on determining the sensor distance from post-consumer PET bottles. The second experiment aimed to evaluate the sensor’s detection ability with varying liquid levels, while the third experiment assessed its detection capability for bottle labels. A digital lux meter integrated with a microcontroller was developed to monitor illuminance in post-consumer PET bottles containing liquid as they moved through a conveyor belt at an average rate of three bottles per second. The implemented methodology successfully detected liquids inside transpare... [more]

Gene expression data are usually known for having a large number of features. Usually, some of these features are irrelevant and redundant. However, in some cases, all features, despite being numerous, show high importance and contribute to the data analysis. In a similar fashion, gene expression data sometimes have limited instances with a high rate of imbalance among the classes. This can limit the exposure of a classification model to instances of different categories, thereby influencing the performance of the model. In this study, we proposed a cancer detection approach that utilized data preprocessing techniques such as oversampling, feature selection, and classification models. The study used SVMSMOTE for the oversampling of the six examined datasets. Further, we examined different techniques for feature selection using dimension reduction methods and classifier-based feature ranking and selection. We trained six machine learning algorithms, using repeated 5-fold cross-validatio... [more]

Geometallurgy integrates aspects of geology, metallurgy, and mine planning in order to improve decision making in mining schedules. A geometallurgical model is a 3D space that is typically synthesized from early-stage small-scale samples and is composed of several metallurgical units, or domains. This work explores the synthesis of a geometallurgical model for a copper deposit using a purely data-driven unsupervised approach. To this end, a dataset of 1112 drill samples is used, which are clustered using different methods, namely, k-means, hierarchical clustering (AGG), self-organizing maps (SOM), and DBSCAN. Two cluster validity indices (Silhouette and Calinski−Harabasz) are used to select the final model. To validate the potential of the proposed approach, a simulated economic evaluation is conducted. Results demonstrate that k-means exhibits a better performance in terms of modeling and that using the obtained geometallurgical model for mining scheduling increases the project’s Net... [more]

Machine learning assists with food process optimization techniques by developing a model to predict the optimal solution for given input data. Machine learning includes unsupervised and supervised learning, data pre-processing, feature engineering, model selection, assessment, and optimization methods. Various problems with food processing optimization could be resolved using these techniques. Machine learning is increasingly being used in the food industry to improve production efficiency, reduce waste, and create personalized customer experiences. Machine learning may be used to improve ingredient utilization and save costs, automate operations such as packing and labeling, and even forecast consumer preferences to develop personalized products. Machine learning is also being used to identify food safety hazards before they reach the consumer, such as contaminants or spoiled food. The usage of machine learning in the food sector is predicted to rise in the near future as more busines... [more]

The development and optimization of lipid nanoparticle (LNP) formulations through hydrodynamic mixing is critical for ensuring the efficient and cost-effective supply of vaccines. Continuous LNP formation through microfluidic mixing can overcome manufacturing bottlenecks and enable the production of nucleic acid vaccines and therapeutics. Predictive process models developed within a QbD Biopharma 4.0 approach can ensure the quality and consistency of the manufacturing process. This study highlights the importance of continuous LNP formation through microfluidic mixing in ensuring high-quality, in-specification production. Both empty and nucleic acid-loaded LNPs are characterized, followed by a TFF/buffer exchange to obtain process parameters for the envisioned continuous SPTFF. It is shown that LNP generation by pipetting leads to a less preferable product when compared to continuous mixing due to the heterogeneity and large particle size of the resulting LNPs (86−104 nm). Particle siz... [more]

Pharmaceutical manufacturing processes are moving towards automation and real-time process monitoring with the help of process analytical technologies (PATs) and predictive process models representing the real system. In this paper, we present a digital twin developed for an adjuvant manufacturing process involving a microfluidic formation of lipid particles. The twin uses a hybrid model for estimating the current state of the process and predicting system behavior in real time. The twin is used to control the adjuvant particle size, a critical quality attribute, by varying process parameters such as the temperature and inlet flow rates. We describe steps in the design and implementation of the twin, starting from the conception of the mechanistic model, up to the generation of its surrogate model used as state estimator, PATs and the setup of the information technology—Operational technology architecture. We demonstrate the performance of the twin by introducing different disturbances... [more]

To boost the operational performance of a non-aqueous DES electrolyte-based vanadium-iron redox flow battery (RFB), our previous work proposed a double-layer porous electrode spliced by carbon paper and graphite felt. However, this electrode’s architecture still needs to be further optimized under different operational conditions. Hence, this paper proposes a multi-layer artificial neural network (ANN) model to predict the relationship between vanadium-iron RFB’s performance and double-layer electrode structural characteristics. A training dataset of ANN is generated by three-dimensional finite-element numerical simulations of the galvanostatic discharging process. In addition, a genetic algorithm (GA) is coupled to an ANN regression training process for optimizing the model parameters to elevate the accuracy of ANN prediction. The novelty of this work lies in this modified optimal method of a double-layer electrode for non-aqueous RFB driven by a machine learning (ML) model coupled wi... [more]

Several metaheuristic algorithms have been implemented to solve global optimization issues. Nevertheless, these approaches require more enhancement to strike a suitable harmony between exploration and exploitation. Consequently, this paper proposes improving the arithmetic optimization algorithm (AOA) to solve engineering optimization issues based on the cuckoo search algorithm called AOACS. The developed approach uses cuckoo search algorithm operators to improve the ability of the exploitation operations of AOA. AOACS enhances the convergence ratio of the presented technique to find the optimum solution. The performance of the AOACS is examined using 23 benchmark functions and CEC-2019 functions to show the ability of the proposed work to solve different numerical optimization problems. The proposed AOACS is evaluated using four engineering design problems: the welded beam, the three-bar truss, the stepped cantilever beam, and the speed reducer design. Finally, the results of the prop... [more]

The initial design phase for offshore wind farms does not require complete geotechnical mapping and individual cone penetration testing (CPT) for each expected turbine location. Instead, background information from open source studies and previous historic records for geology and seismic data are typically used at this early stage to develop a preliminary ground model. This study focuses specifically on the interpolation and extrapolation of cone penetration test (CPT) data. A detailed methodology is presented for the process of using a limited number of CPTs to characterise the geotechnical behavior of an offshore site using artificial neural networks. In the presented study, the optimised neural network achieved a predictive error of 0.067. Accuracy is greatest at depths of less than 10 m. The pitfalls of using machine learning for geospatial interpolation are explained and discussed.

Injecting power plant flue gas into a goaf stores CO2 in the flue gas and effectively prevents the spontaneous combustion of the coal remaining in the goaf. Here, we investigated the adsorption behavior of three types of coal at normal temperature and pressure using a self-developed adsorption experimental device. We used a specific surface area and porosity analyzer to study the effects of pore structure, mineral content, and moisture content on CO2 adsorption in coal. Based on the experimental data, we designed a multifactor CO2 adsorption prediction model based on a backpropagation (BP) neural network. The results indicated that the pore size of most micropores in coal was in the range of 0.5−0.7 and 0.8−0.9 nm. The specific surface area and pore volume were positively correlated with the CO2-saturated adsorption capacity, whereas the mean pore diameter, mineral content, and moisture content were inversely associated with the CO2-saturated adsorption amount. The accuracy of the mult... [more]

The share of residential building energy consumption in global energy consumption has rapidly increased after the COVID-19 crisis. The accurate prediction of energy consumption under different indoor and outdoor conditions is an essential step towards improving energy efficiency and reducing carbon footprints in the residential building sector. In this paper, a PSO-optimized random forest classification algorithm is proposed to identify the most important factors contributing to residential heating energy consumption. A self-organizing map (SOM) approach is applied for feature dimensionality reduction, and an ensemble classification model based on the stacking method is trained on the dimensionality-reduced data. The results show that the stacking model outperforms the other models with an accuracy of 95.4% in energy consumption prediction. Finally, a causal inference method is introduced in addition to Shapley Additive Explanation (SHAP) to explore and analyze the factors influencing... [more]

At present, the condition assessment of transformer winding based on frequency response analysis (FRA) measurements demands skilled personnel. Despite many research efforts in the last decade, there is still no definitive methodology for the interpretation and condition assessment of transformer winding based on FRA results, and this is a major challenge for the industrial application of the FRA method. To overcome this challenge, this paper proposes a transformer condition assessment (TCA) algorithm, which is based on numerical indices, and a supervised machine learning technique to develop a method for the automatic interpretation of FRA results. For this purpose, random forest (RF) classifiers were developed for the first time to identify the condition of transformer winding and classify different faults in the transformer windings. Mainly, six common states of the transformer were classified in this research, i.e., healthy transformer, healthy transformer with saturated core, mecha... [more]

To improve the viability of nuclear power plants, there is a need to reduce their operational costs. Operational costs account for a significant portion of a plant’s yearly budget, due to their scheduled-based maintenance approach. In order to reduce these costs, proactive methods are required that estimate and forecast the state of a machine in real time to optimize maintenance schedules. In this research, we use Bayesian networks to develop a framework that can forecast the remaining useful life of a centrifugal pump. To do so, we integrate survival analysis with Bayesian statistics to forecast the health of the pump conditional to its current state. We complete our research by successfully using the Bayesian network on a case study. This solution provides an informed probabilistic viewpoint of the pumping system for the purpose of predictive maintenance.

Accurately predicting well productivity is crucial for optimizing gas production and maximizing recovery from tight gas reservoirs. Machine learning (ML) techniques have been applied to build predictive models for the well productivity, but their high complexity and low interpretability can hinder their practical application. This study proposes using interpretable ML solutions, SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME), to provide explicit explanations of the ML prediction model. The study uses data from the Eastern Sulige tight gas field in the Ordos Basin, China, containing various geological and engineering factors. The results show that the gradient boosting decision tree model exhibits superior predictive performance compared to other ML models. The global interpretation using SHAP provides insights into the overall impact of these factors, while the local interpretation using SHAP and LIME offers individualized explanations o... [more]

In the medical domain, early identification of cardiovascular issues poses a significant challenge. This study enhances heart disease prediction accuracy using machine learning techniques. Six algorithms (random forest, K-nearest neighbor, logistic regression, Naïve Bayes, gradient boosting, and AdaBoost classifier) are utilized, with datasets from the Cleveland and IEEE Dataport. Optimizing model accuracy, GridsearchCV, and five-fold cross-validation are employed. In the Cleveland dataset, logistic regression surpassed others with 90.16% accuracy, while AdaBoost excelled in the IEEE Dataport dataset, achieving 90% accuracy. A soft voting ensemble classifier combining all six algorithms further enhanced accuracy, resulting in a 93.44% accuracy for the Cleveland dataset and 95% for the IEEE Dataport dataset. This surpassed the performance of the logistic regression and AdaBoost classifiers on both datasets. This study’s novelty lies in the use of GridSearchCV with five-fold cross-valida... [more]

The timely and effective fault diagnosis method is critical to the operation of the air-conditioning system and energy saving of buildings. In this study, a novel fault diagnosis method was proposed. It is combined with the signal demodulation method and machine learning method. The fault signals are demodulated by the demodulation method based on time-frequency analysis and principal component analysis (DPCA). The modulation characteristics of the principal component and DPCA sets with stronger features are obtained. Compared with time domain sets, the correct rate was increased by 16.38%. Then, as a machine learning method, the Visual Geometry Group—Principal Component Analysis (VGG-PCA) model is proposed in this study. The application potential of this model is discussed by using evaluation indexes of fault diagnosis performance and two typical faults of air conditioning systems. Compared with the other two convolution neural network models, the correct rate was increased by 17.1% a... [more]

Due to the progressive digitalization of the industry, more and more data is available not only as digitally stored data but also as online data via standardized interfaces. This not only leads to further improvements in process modeling through more data but also opens up the possibility of linking process models with online data of the process plants. As a result, digital representations of the processes emerge, which are called Digital Twins. To further improve these Digital Twins, process models in general, and the challenging process design and development task itself, the new data availability is paired with recent advancements in the field of machine learning. This paper presents a case study of an ANN for the parameter estimation of a Steric Mass Action (SMA)-based mixed-mode chromatography model. The results are used to exemplify, discuss, and point out the effort/benefit balance of ANN. To set the results in a wider context, the results and use cases of other working groups a... [more]

Skin lesions affect millions of people worldwide. They can be easily recognized based on their typically abnormal texture and color but are difficult to diagnose due to similar symptoms among certain types of lesions. The motivation for this study is to collate and analyze machine learning (ML) applications in skin lesion research, with the goal of encouraging the development of automated systems for skin disease diagnosis. To assist dermatologists in their clinical diagnosis, several skin image datasets have been developed and published online. Such efforts have motivated researchers and medical staff to develop automatic skin diagnosis systems using image segmentation and classification processes. This paper summarizes the fundamental steps in skin lesion diagnosis based on papers mainly published since 2013. The applications of ML methods (including traditional ML and deep learning (DL)) in skin disease recognition are reviewed based on their contributions, methods, and achieved res... [more]