Effect of Data Scaling Methods on Machine Learning Algorithms and Model Performance

A GA-stacking ensemble approach for forecasting energy consumption in a smart household: A comparative study of ensemble methods

The considerable amount of energy utilized by buildings has led to various environmental challenges that adversely impact human existence. Predicting buildings' energy usage is commonly acknowledged as encouraging energy efficiency and enabling well-informed decision-making, ultimately leading to decreased energy consumption. Implementing eco-friendly architectural designs is paramount in mitigating energy consumption, particularly in recently constructed structures. This study utilizes clustering analysis on the original dataset to capture complex consumption patterns over various periods. The analysis yields two distinct subsets that represent low and high consumption patterns and an additional subset that exclusively encompasses weekends, attributed to the specific behavior of occupants. Ensemble models have become increasingly popular due to advancements in machine learning techniques. This research utilizes three discrete algorithms, namely Artificial Neural Network (ANN), K-nearest neighbors (KNN), and Decision Trees (DT). In addition, the application employs three more machine learning algorithms bagging and boosting: Random Forest (RF), Extreme Gradient Boosting (XGB), and Gradient Boosting Trees (GBT). To augment the accuracy of predictions, a stacking ensemble methodology is employed, wherein the forecasts generated by many algorithms are combined. Given the obtained outcomes, a thorough examination is undertaken, encompassing the techniques of stacking, bagging, and boosting, to conduct a comprehensive comparative study. It is pertinent to highlight that the stacking technique consistently exhibits superior performance relative to alternative ensemble methodologies across a spectrum of heterogeneous datasets. Furthermore, using a genetic algorithm enables the optimization of the combination of base learners, resulting in a notable enhancement in prediction accuracy. After implementing this optimization technique, GA-Stacking demonstrated remarkable performance in Mean Absolute Percentage Error (MAPE) scores. The improvement observed was substantial, surpassing 90 percent for all datasets. In addition, in subset-1, subset-2, and subset-3, the achieved R2 scores were 0.983, 0.985, and 0.999, respectively. This represents a substantial advancement in forecasting the energy consumption of residential buildings. Such progress underscores the potential advantages of integrating this framework into the practices of building designers, thereby fostering informed decision-making, design management, and optimization prior to construction.

Optimizing Rare Disease Gait Classification through Data Balancing and Generative AI: Insights from Hereditary Cerebellar Ataxia

The interpretability of gait analysis studies in people with rare diseases, such as those with primary hereditary cerebellar ataxia (pwCA), is frequently limited by the small sample sizes and unbalanced datasets. The purpose of this study was to assess the effectiveness of data balancing and generative artificial intelligence (AI) algorithms in generating synthetic data reflecting the actual gait abnormalities of pwCA. Gait data of 30 pwCA (age: 51.6 ± 12.2 years; 13 females, 17 males) and 100 healthy subjects (age: 57.1 ± 10.4; 60 females, 40 males) were collected at the lumbar level with an inertial measurement unit. Subsampling, oversampling, synthetic minority oversampling, generative adversarial networks, and conditional tabular generative adversarial networks (ctGAN) were applied to generate datasets to be input to a random forest classifier. Consistency and explainability metrics were also calculated to assess the coherence of the generated dataset with known gait abnormalities of pwCA. ctGAN significantly improved the classification performance compared with the original dataset and traditional data augmentation methods. ctGAN are effective methods for balancing tabular datasets from populations with rare diseases, owing to their ability to improve diagnostic models with consistent explainability.

Table 0; documenting the steps to go from clinical database to research dataset

OBJECTIVES

Data-driven decision support tools have been increasingly recognized to transform health care. However, such tools are often developed on predefined research datasets without adequate knowledge of the origin of this data and how it was selected. How a dataset is extracted from a clinical database can profoundly impact the validity, interpretability and interoperability of the dataset, and downstream analyses, yet is rarely reported. Therefore, we present a case study illustrating how a definitive patient list was extracted from a clinical source database and how this can be reported.

STUDY DESIGN AND SETTING

A single-center observational study was performed at an academic hospital in the Netherlands to illustrate the impact of selecting a definitive patient list for research from a clinical source database, and the importance of documenting this process. All admissions from the critical care database admitted between January 1, 2013, and January 1, 2023, were used.

RESULTS

An interdisciplinary team collaborated to identify and address potential sources of data insufficiency and uncertainty. We demonstrate a stepwise data preparation process, reducing the clinical source database of 54,218 admissions to a definitive patient list of 21,553 admissions. Transparent documentation of the data preparation process improves the quality of the definitive patient list before analysis of the corresponding patient data. This study generated seven important recommendations for preparing observational health-care data for research purposes.

CONCLUSION

Documenting data preparation is essential for understanding a research dataset originating from a clinical source database before analyzing health-care data. The findings contribute to establishing data standards and offer insights into the complexities of preparing health-care data for scientific investigation. Meticulous data preparation and documentation thereof will improve research validity and advance critical care.

Machine learning prediction of nutritional status among pregnant women in Bangladesh: Evidence from Bangladesh demographic and health survey 2017-18

AIM

Malnutrition in pregnant women significantly affects both mother and child health. This research aims to identify the best machine learning (ML) techniques for predicting the nutritional status of pregnant women in Bangladesh and detect the most essential features based on the best-performed algorithm.

METHODS

This study used retrospective cross-sectional data from the Bangladeshi Demographic and Health Survey 2017-18. Different feature transformations and machine learning classifiers were applied to find the best transformation and classification model.

RESULTS

This investigation found that robust scaling outperformed all feature transformation methods. The result shows that the Random Forest algorithm with robust scaling outperforms all other machine learning algorithms with 74.75% accuracy, 57.91% kappa statistics, 73.36% precision, 73.08% recall, and 73.09% f1 score. In addition, the Random Forest algorithm had the highest precision (76.76%) and f1 score (71.71%) for predicting the underweight class, as well as an expected precision of 82.01% and f1 score of 83.78% for the overweight/obese class when compared to other algorithms with a robust scaling method. The respondent's age, wealth index, region, husband's education level, husband's age, and occupation were crucial features for predicting the nutritional status of pregnant women in Bangladesh.

CONCLUSION

The proposed classifier could help predict the expected outcome and reduce the burden of malnutrition among pregnant women in Bangladesh.

Comparing Performances of Predictive Models of Toxicity after Radiotherapy for Breast Cancer Using Different Machine Learning Approaches

PURPOSE

Different ML models were compared to predict toxicity in RT on a large cohort (n = 1314).

METHODS

The endpoint was RTOG G2/G3 acute toxicity, resulting in 204/1314 patients with the event. The dataset, including 25 clinical, anatomical, and dosimetric features, was split into 984 for training and 330 for internal tests. The dataset was standardized; features with a high p-value at univariate LR and with Spearman ρ>0.8 were excluded; synthesized data of the minority were generated to compensate for class imbalance. Twelve ML methods were considered. Model optimization and sequential backward selection were run to choose the best models with a parsimonious feature number. Finally, feature importance was derived for every model.

RESULTS

The model's performance was compared on a training-test dataset over different metrics: the best performance model was LightGBM. Logistic regression with three variables (LR3) selected via bootstrapping showed performances similar to the best-performing models. The AUC of test data is slightly above 0.65 for the best models (highest value: 0.662 with LightGBM).

CONCLUSIONS

No model performed the best for all metrics: more complex ML models had better performances; however, models with just three features showed performances comparable to the best models using many (n = 13-19) features.

Machine learning, a powerful tool for the prediction of BiVO4 nanoparticles efficiency in photocatalytic degradation of organic dyes

Wastewater pollution caused by organic dyes is a growing concern due to its negative impact on human health and aquatic life. To tackle this issue, the use of advanced wastewater treatment with nano photocatalysts has emerged as a promising solution. However, experimental procedures for identifying the optimal conditions for dye degradation could be time-consuming and expensive. To overcome this, machine learning methods have been employed to predict the degradation of organic dyes in a more efficient manner by recognizing patterns in the process and addressing its feasibility. The objective of this study is to develop a machine learning model to predict the degradation of organic dyes and identify the main variables affecting the photocatalytic degradation capacity and removal of organic dyes from wastewater. Nine machine learning algorithms were tested including multiple linear regression, polynomial regression, decision trees, random forest, adaptive boosting, extreme gradient boosting, k-nearest neighbors, support vector machine, and artificial neural network. The study found that the XGBoosting algorithm outperformed the other models, making it ideal for predicting the photocatalytic degradation capacity of BiVO4. The results suggest that XGBoost is a suitable model for predicting the photocatalytic degradation of wastewater using BiVO4 with different dopants.

Improving Prediction of Survival for Extremely Premature Infants Born at 23 to 29 Weeks Gestational Age in the Neonatal Intensive Care Unit: Development and Evaluation of Machine Learning Models

BACKGROUND

Infants born at extremely preterm gestational ages are typically admitted to the neonatal intensive care unit (NICU) after initial resuscitation. The subsequent hospital course can be highly variable, and despite counseling aided by available risk calculators, there are significant challenges with shared decision-making regarding life support and transition to end-of-life care. Improving predictive models can help providers and families navigate these unique challenges.

OBJECTIVE

Machine learning methods have previously demonstrated added predictive value for determining intensive care unit outcomes, and their use allows consideration of a greater number of factors that potentially influence newborn outcomes, such as maternal characteristics. Machine learning-based models were analyzed for their ability to predict the survival of extremely preterm neonates at initial admission.

METHODS

Maternal and newborn information was extracted from the health records of infants born between 23 and 29 weeks of gestation in the Medical Information Mart for Intensive Care III (MIMIC-III) critical care database. Applicable machine learning models predicting survival during the initial NICU admission were developed and compared. The same type of model was also examined using only features that would be available prepartum for the purpose of survival prediction prior to an anticipated preterm birth. Features most correlated with the predicted outcome were determined when possible for each model.

RESULTS

Of included patients, 37 of 459 (8.1%) expired. The resulting random forest model showed higher predictive performance than the frequently used Score for Neonatal Acute Physiology With Perinatal Extension II (SNAPPE-II) NICU model when considering extremely preterm infants of very low birth weight. Several other machine learning models were found to have good performance but did not show a statistically significant difference from previously available models in this study. Feature importance varied by model, and those of greater importance included gestational age; birth weight; initial oxygenation level; elements of the APGAR (appearance, pulse, grimace, activity, and respiration) score; and amount of blood pressure support. Important prepartum features also included maternal age, steroid administration, and the presence of pregnancy complications.

CONCLUSIONS

Machine learning methods have the potential to provide robust prediction of survival in the context of extremely preterm births and allow for consideration of additional factors such as maternal clinical and socioeconomic information. Evaluation of larger, more diverse data sets may provide additional clarity on comparative performance.

Applications of Machine Learning (ML) and Mathematical Modeling (MM) in Healthcare with Special Focus on Cancer Prognosis and Anticancer Therapy: Current Status and Challenges

The use of data-driven high-throughput analytical techniques, which has given rise to computational oncology, is undisputed. The widespread use of machine learning (ML) and mathematical modeling (MM)-based techniques is widely acknowledged. These two approaches have fueled the advancement in cancer research and eventually led to the uptake of telemedicine in cancer care. For diagnostic, prognostic, and treatment purposes concerning different types of cancer research, vast databases of varied information with manifold dimensions are required, and indeed, all this information can only be managed by an automated system developed utilizing ML and MM. In addition, MM is being used to probe the relationship between the pharmacokinetics and pharmacodynamics (PK/PD interactions) of anti-cancer substances to improve cancer treatment, and also to refine the quality of existing treatment models by being incorporated at all steps of research and development related to cancer and in routine patient care. This review will serve as a consolidation of the advancement and benefits of ML and MM techniques with a special focus on the area of cancer prognosis and anticancer therapy, leading to the identification of challenges (data quantity, ethical consideration, and data privacy) which are yet to be fully addressed in current studies.

Fractal Dimension as a discriminative feature for high accuracy classification in motor imagery EEG-based brain-computer interface

BACKGROUND AND OBJECTIVE

The brain-computer interface (BCI) technology acquires human brain electrical signals, which can be effectively and successfully used to control external devices, potentially supporting subjects suffering from motor impairments in the interaction with the environment. To this aim, BCI systems must correctly decode and interpret neurophysiological signals reflecting the intention of the subjects to move. Therefore, the accurate classification of single events in motor tasks represents a fundamental challenge in ensuring efficient communication and control between users and BCIs. Movement-associated changes in electroencephalographic (EEG) sensorimotor rhythms, such as event-related desynchronization (ERD), are well-known features of discriminating motor tasks. Fractal dimension (FD) can be used to evaluate the complexity and self-similarity in brain signals, potentially providing complementary information to frequency-based signal features.

METHODS

In the present work, we introduce FD as a novel feature for subject-independent event classification, and we test several machine learning (ML) models in behavioural tasks of motor imagery (MI) and motor execution (ME).

RESULTS

Our results show that FD improves the classification accuracy of ML compared to ERD. Furthermore, unilateral hand movements have higher classification accuracy than bilateral movements in both MI and ME tasks.

CONCLUSIONS

These results provide further insights into subject-independent event classification in BCI systems and demonstrate the potential of FD as a discriminative feature for EEG signals.

Prediction of the synergistic effect of antimicrobial peptides and antimicrobial agents via supervised machine learning

BACKGROUND

Infectious diseases not only cause severe health problems but also burden the healthcare system. Therefore, the effective treatment of those diseases is crucial. Both conventional approaches, such as antimicrobial agents, and novel approaches, like antimicrobial peptides (AMPs), are used to treat infections. However, due to the drawbacks of current approaches, new solutions are still being investigated. One recent approach is the use of AMPs and antimicrobial agents in combination, but determining synergism is with a huge variety of AMPs time-consuming and requires multiple experimental studies. Machine learning (ML) algorithms are widely used to predict biological outcomes, particularly in the field of AMPs, but no previous research reported on predicting the synergistic effects of AMPs and antimicrobial agents.

RESULTS

Several supervised ML models were implemented to accurately predict the synergistic effect of AMPs and antimicrobial agents. The results demonstrated that the hyperparameter-optimized Light Gradient Boosted Machine Classifier (oLGBMC) yielded the best test accuracy of 76.92% for predicting the synergistic effect. Besides, the feature importance analysis reveals that the target microbial species, the minimum inhibitory concentrations (MICs) of the AMP and the antimicrobial agents, and the used antimicrobial agent were the most important features for the prediction of synergistic effect, which aligns with recent experimental studies in the literature.

CONCLUSION

This study reveals that ML algorithms can predict the synergistic activity of two different antimicrobial agents without the need for complex and time-consuming experimental procedures. The implications support that the ML models may not only reduce the experimental cost but also provide validation of experimental procedures.

Machine Learning Approach for Analyzing 3-Year Outcomes of Patients with Brain Arteriovenous Malformation (AVM) after Stereotactic Radiosurgery (SRS)

A cerebral arteriovenous malformation (AVM) is a tangle of abnormal blood vessels that irregularly connects arteries and veins. Stereotactic radiosurgery (SRS) has been shown to be an effective treatment for AVM patients, but the factors associated with AVM obliteration remains a matter of debate. In this study, we aimed to develop a model that can predict whether patients with AVM will be cured 36 months after intervention by means of SRS and identify the most important predictors that explain the probability of being cured. A machine learning (ML) approach was applied using decision tree (DT) and logistic regression (LR) techniques on historical data (sociodemographic, clinical, treatment, angioarchitecture, and radiosurgery procedure) of 202 patients with AVM who underwent SRS at the Instituto de Radiocirugía del Perú (IRP) between 2005 and 2018. The LR model obtained the best results for predicting AVM cure with an accuracy of 0.92, sensitivity of 0.93, specificity of 0.89, and an area under the curve (AUC) of 0.98, which shows that ML models are suitable for predicting the prognosis of medical conditions such as AVM and can be a support tool for medical decision-making. In addition, several factors were identified that could explain whether patients with AVM would be cured at 36 months with the highest likelihood: the location of the AVM, the occupation of the patient, and the presence of hemorrhage.

Predicting CPAP failure after less invasive surfactant administration (LISA) in preterm infants by machine learning model on vital parameter data: a pilot study

Objective. Less invasive surfactant administration (LISA) has been introduced to preterm infants with respiratory distress syndrome on continuous positive airway pressure (CPAP) support in order to avoid intubation and mechanical ventilation. However, after this LISA procedure, a significant part of infants fails CPAP treatment (CPAP-F) and requires intubation in the first 72 h of life, which is associated with worse complication free survival chances. The aim of this study was to predict CPAP-F after LISA, based on machine learning (ML) analysis of high resolution vital parameter monitoring data surrounding the LISA procedure.Approach. Patients with a gestational age (GA) <32 weeks receiving LISA were included. Vital parameter data was obtained from a data warehouse. Physiological features (HR, RR, peripheral oxygen saturation (SpO2) and body temperature) were calculated in eight 0.5 h windows throughout a period 1.5 h before to 2.5 h after LISA. First, physiological data was analyzed to investigate differences between the CPAP-F and CPAP-Success (CPAP-S) groups. Next, the performance of two types of ML models (logistic regression: LR, support vector machine: SVM) for the prediction of CPAP-F were evaluated.Main results. Of 51 included patients, 18 (35%) had CPAP-F. Univariate analysis showed lower SpO2, temperature and heart rate variability (HRV) before and after the LISA procedure. The best performing ML model showed an area under the curve of 0.90 and 0.93 for LR and SVM respectively in the 0.5 h window directly after LISA, with GA, HRV, respiration rate and SpO2as most important features. Excluding GA decreased performance in both models.Significance. In this pilot study we were able to predict CPAP-F with a ML model of patient monitor signals, with best performance in the first 0.5 h after LISA. Using ML to predict CPAP-F based on vital signals gains insight in (possibly modifiable) factors that are associated with LISA failure and can help to guide personalized clinical decisions in early respiratory management.

Data-driven prediction of the shear capacity of ETS-FRP-strengthened beams in the hybrid 2PKT-ML approach

A new approach that combines analytical two-parameter kinematic theory (2PKT) with machine learning (ML) models for estimating the shear capacity of embedded through-section (ETS)-strengthened reinforced concrete (RC) beams is proposed. The 2PKT was first developed to validate its representativeness and confidence against the available experimental data of ETS-retrofitted RC beams. Given the deficiency of the test data, the developed 2PKT was utilized to generate a large data pool with 2643 samples. The aim was to optimize the ML algorithms, namely, the random forest, extreme gradient boosting (XGBoost), light gradient boosting machine, and artificial neural network (ANN) algorithm. The optimized ANN model exhibited the highest accuracy in predicting the total shear strength of ETS-strengthened beams and ETS shear contribution. In terms of predicting the total shear strength of ETS-strengthened beams, the ANN model achieved R2 values of 0.99, 0.98, and 0.96 for the training, validation, and testing data, respectively. By contrast, the ANN model could predict ETS shear contribution with high accuracy, with R2 values of 0.99, 0.99, and 0.97 for the training, validation, and testing data, respectively. Then, the effects of all design variables on the shear capacity of the ETS-strengthened beams were investigated using the hybrid 2PKT-ML. The obtained trends could well appraise the reasonability of the proposed approach.

DVNE-DRL: dynamic virtual network embedding algorithm based on deep reinforcement learning

Virtual network embedding (VNE), as the key challenge of network resource management technology, lies in the contradiction between online embedding decision and pursuing long-term average revenue goals. Most of the previous work ignored the dynamics in Virtual Network (VN) modeling, or could not automatically detect the complex and time-varying network state to provide a reasonable network embedding scheme. In view of this, we model a network embedding framework where the topology and resource allocation change dynamically with the number of network users and workload, and then introduce a deep reinforcement learning method to solve the VNE problem. Further, a dynamic virtual network embedding algorithm based on Deep Reinforcement Learning (DRL), named DVNE-DRL, is proposed. In DVNE-DRL, VNE is modeled as a Markov Decision Process (MDP), and then deep learning is introduced to perceive the current network state through historical data and embedded knowledge, while utilizing reinforcement learning decision-making capabilities to implement the network embedding process. In addition, we improve the method of feature extraction and matrix optimization, and consider the characteristics of virtual network and physical network together to alleviate the problem of redundancy and slow convergence. The simulation results show that compared with the existing advanced algorithms, the acceptance rate and average revenue of DVNE-DRL are increased by about 25% and 35%, respectively.

Cancer Metastasis Prediction and Genomic Biomarker Identification through Machine Learning and eXplainable Artificial Intelligence in Breast Cancer Research

AIM

Method: This research presents a model combining machine learning (ML) techniques and eXplainable artificial intelligence (XAI) to predict breast cancer (BC) metastasis and reveal important genomic biomarkers in metastasis patients.

METHOD

A total of 98 primary BC samples was analyzed, comprising 34 samples from patients who developed distant metastases within a 5-year follow-up period and 44 samples from patients who remained disease-free for at least 5 years after diagnosis. Genomic data were then subjected to biostatistical analysis, followed by the application of the elastic net feature selection method. This technique identified a restricted number of genomic biomarkers associated with BC metastasis. A light gradient boosting machine (LightGBM), categorical boosting (CatBoost), Extreme Gradient Boosting (XGBoost), Gradient Boosting Trees (GBT), and Ada boosting (AdaBoost) algorithms were utilized for prediction. To assess the models' predictive abilities, the accuracy, F1 score, precision, recall, area under the ROC curve (AUC), and Brier score were calculated as performance evaluation metrics. To promote interpretability and overcome the "black box" problem of ML models, a SHapley Additive exPlanations (SHAP) method was employed.

RESULTS

The LightGBM model outperformed other models, yielding remarkable accuracy of 96% and an AUC of 99.3%. In addition to biostatistical evaluation, in XAI-based SHAP results, increased expression levels of TSPYL5, ATP5E, CA9, NUP210, SLC37A1, ARIH1, PSMD7, UBQLN1, PRAME, and UBE2T (p ≤ 0.05) were found to be associated with an increased incidence of BC metastasis. Finally, decreased levels of expression of CACTIN, TGFB3, SCUBE2, ARL4D, OR1F1, ALDH4A1, PHF1, and CROCC (p ≤ 0.05) genes were also determined to increase the risk of metastasis in BC.

CONCLUSION

The findings of this study may prevent disease progression and metastases and potentially improve clinical outcomes by recommending customized treatment approaches for BC patients.

Global land subsidence mapping reveals widespread loss of aquifer storage capacity

Groundwater overdraft gives rise to multiple adverse impacts including land subsidence and permanent groundwater storage loss. Existing methods are unable to characterize groundwater storage loss at the global scale with sufficient resolution to be relevant for local studies. Here we explore the interrelation between groundwater stress, aquifer depletion, and land subsidence using remote sensing and model-based datasets with a machine learning approach. The developed model predicts global land subsidence magnitude at high spatial resolution (~2 km), provides a first-order estimate of aquifer storage loss due to consolidation of ~17 km3/year globally, and quantifies key drivers of subsidence. Roughly 73% of the mapped subsidence occurs over cropland and urban areas, highlighting the need for sustainable groundwater management practices over these areas. The results of this study aid in assessing the spatial extents of subsidence in known subsiding areas, and in locating unknown groundwater stressed regions.

Enhancing Diagnosis of Anterior and Inferior Myocardial Infarctions Using UWB Radar and AI-Driven Feature Fusion Approach

Despite significant improvement in prognosis, myocardial infarction (MI) remains a major cause of morbidity and mortality around the globe. MI is a life-threatening cardiovascular condition that requires prompt diagnosis and appropriate treatment. The primary objective of this research is to identify instances of anterior and inferior myocardial infarction by utilizing data obtained from Ultra-wideband radar technology in a hospital for patients of anterior and inferior MI. The collected data is preprocessed to extract spectral features. A novel feature engineering approach is designed to fuse temporal features and class prediction probability features derived from the spectral feature dataset. Several well-known machine learning models are implemented and fine-tuned to obtain optimal performance in the detection of anterior and inferior MI. The results demonstrate that integration of the fused feature set with machine learning models results in a notable improvement in both the accuracy and precision of MI detection. Notably, random forest (RF) and k-nearest neighbor showed superb performance with an accuracy of 98.8%. For demonstrating the capacity of models to generalize, K-fold cross-validation is carried out, wherein RF exhibits a mean accuracy of 99.1%. Furthermore, the examination of computational complexity indicates a low computational complexity, thereby indicating computational efficiency.

Towards artificial intelligence-enabled extracellular vesicle precision drug delivery

Extracellular Vesicles (EVs), particularly exosomes, recently exploded into nanomedicine as an emerging drug delivery approach due to their superior biocompatibility, circulating stability, and bioavailability in vivo. However, EV heterogeneity makes molecular targeting precision a critical challenge. Deciphering key molecular drivers for controlling EV tissue targeting specificity is in great need. Artificial intelligence (AI) brings powerful prediction ability for guiding the rational design of engineered EVs in precision control for drug delivery. This review focuses on cutting-edge nano-delivery via integrating large-scale EV data with AI to develop AI-directed EV therapies and illuminate the clinical translation potential. We briefly review the current status of EVs in drug delivery, including the current frontier, limitations, and considerations to advance the field. Subsequently, we detail the future of AI in drug delivery and its impact on precision EV delivery. Our review discusses the current universal challenge of standardization and critical considerations when using AI combined with EVs for precision drug delivery. Finally, we will conclude this review with a perspective on future clinical translation led by a combined effort of AI and EV research.

Energy Prediction and Optimization for Smart Homes with Weather Metric-Weight Coefficients

Home appliances are considered to account for a large portion of smart homes' energy consumption. This is due to the abundant use of IoT devices. Various home appliances, such as heaters, dishwashers, and vacuum cleaners, are used every day. It is thought that proper control of these home appliances can reduce significant amounts of energy use. For this purpose, optimization techniques focusing mainly on energy reduction are used. Current optimization techniques somewhat reduce energy use but overlook user convenience, which was the main goal of introducing home appliances. Therefore, there is a need for an optimization method that effectively addresses the trade-off between energy saving and user convenience. Current optimization techniques should include weather metrics other than temperature and humidity to effectively optimize the energy cost of controlling the desired indoor setting of a smart home for the user. This research work involves an optimization technique that addresses the trade-off between energy saving and user convenience, including the use of air pressure, dew point, and wind speed. To test the optimization, a hybrid approach utilizing GWO and PSO was modeled. This work involved enabling proactive energy optimization using appliance energy prediction. An LSTM model was designed to test the appliances' energy predictions. Through predictions and optimized control, smart home appliances could be proactively and effectively controlled. First, we evaluated the RMSE score of the predictive model and found that the proposed model results in low RMSE values. Second, we conducted several simulations and found the proposed optimization results to provide energy cost savings used in appliance control to regulate the desired indoor setting of the smart home. Energy cost reduction goals using the optimization strategies were evaluated for seasonal and monthly patterns of data for result verification. Hence, the proposed work is considered a better candidate solution for proactively optimizing the energy of smart homes.

Logistic random forest boosting technique for Alzheimer’s diagnosis

Alzheimer's disease (AD) is a common and well-known neurodegenerative condition that causes cognitive impairment. In the field of medicine, it is the "nervous system" disorder that has received the most attention. Despite this extensive research, there is no treatment or strategy to slow or stop its spread. Nevertheless, there are a variety of options (medication and non-medication alternatives) that may aid in the treatment of AD symptoms at their various phases, thereby enhancing the patient's quality of life. As AD advances over time, it is necessary to treat patients at their various stages appropriately. As a result, detecting and classifying AD phases prior to symptom treatment can be beneficial. Approximately twenty years ago, the rate of progress in the field of machine learning (ML) accelerated dramatically. Using ML methods, this study focuses on early AD identification. The "Alzheimer's Disease Neuroimaging Initiative" (ADNI) dataset was subjected to exhaustive testing for AD identification. The purpose was to classify the dataset into three groups: AD, "Cognitive Normal" (CN), and "Late Mild Cognitive Impairment" (LMCI). In this paper, we present the ensemble model Logistic Random Forest Boosting (LRFB), representing the ensemble of “Logistic Regression” (LR), “Random Forest” (RF), and “Gradient Boost” (GB). The proposed LRFB outperformed LR, RF, GB, “k-Nearest Neighbour” (k-NN), “Multi-Layer Perceptron” (MLP), “Support Vector Machine” (SVM), “AdaBoost” (AB), “Naïve Bayes” (NB), “XGBoost” (XGB), “Decision Tree” (DT), and other ensemble ML models with respect to the performance metrics “Accuracy” (Acc), “Recall” (Rec), “Precision” (Prec), and “F1-Score” (FS).

Identifying two distinct subphenotypes of patent ductus arteriosus in preterm infants using machine learning

To use unsupervised machine learning to identify potential subphenotypes of preterm infants with patent ductus arteriosus (PDA). The study was conducted retrospectively at a neonatal intensive care unit in Brazil. Patients with a gestational age < 28 weeks who had undergone at least one echocardiogram within the first two weeks of life and had PDA size > 1.5 or LA/AO ratio > 1.5 were included. Agglomerative hierarchical clustering on principal components was used to divide the data into different clusters based on common characteristics. Two distinct subphenotypes of preterm infants with hemodynamically significant PDA were identified: "inflamed," characterized by high leukocyte, neutrophil, and neutrophil-to-lymphocyte ratio, and "respiratory acidosis," characterized by low pH and high pCO2 levels.    Conclusions: This study suggests that there may be two distinct subphenotypes of preterm infants with hemodynamically significant PDA: "inflamed" and "respiratory acidosis." By dividing the population into different subgroups based on common characteristics, it is possible to get a more nuanced understanding of the effectiveness of PDA interventions. What is Known: • Treatment of PDA in preterm infants has been controversial. • Stratification of preterm infants with PDA into subgroups is important in order to determine the best treatment. What is New: • Unsupervised machine learning was used to identify two subphenotypes of preterm infants with hemodynamically significant PDA. • The 'inflamed' cluster was characterized by higher values of leukocyte, neutrophil, and neutrophil-to-lymphocyte ratio. The 'respiratory acidosis' cluster was characterized by lower pH values and higher pCO2 values.

The Increase of Theta Power and Decrease of Alpha/Theta Ratio as a Manifestation of Cognitive Impairment in Parkinson's Disease

In this study, we aim to assess and examine cognitive functions in Parkinson's Disease patients using EEG recordings, with a central focus on characteristics associated with a cognitive decline. Based on neuropsychological evaluation using Mini-Mental State Examination, Montreal Cognitive Assessment, and Addenbrooke's Cognitive Examination-III, 98 participants were divided into three cognitive groups. All the particpants of the study underwent EEG recordings with spectral analysis. The results revealed an increase in the absolute theta power in patients with Parkinson's disease dementia (PD-D) compared to cognitively normal status (PD-CogN, p=0.00997) and a decrease in global relative beta power in PD-D compared to PD-CogN (p=0.0413). An increase in theta relative power in the left temporal region (p=0.0262), left occipital region (p=0.0109), and right occipital region (p=0.0221) were observed in PD-D compared to PD-N. The global alpha/theta ratio and global power spectral ratio significantly decreased in PD-D compared to PD-N (p = 0.001). In conclusion, the increase in relative theta power and the decrease in relative beta power are characteristic changes in EEG recordings in PD patients with cognitive impairment. Identifying these changes can be a useful biomarker and a complementary tool in the neuropsychological diagnosis of cognitive impairment in Parkinson's Disease.

DeepAProt: Deep learning based abiotic stress protein sequence classification and identification tool in cereals

The impact of climate change has been alarming for the crop growth. The extreme weather conditions can stress the crops and reduce the yield of major crops belonging to Poaceae family too, that sustains 50% of the world's food calorie and 20% of protein intake. Computational approaches, such as artificial intelligence-based techniques have become the forefront of prediction-based data interpretation and plant stress responses. In this study, we proposed a novel activation function, namely, Gaussian Error Linear Unit with Sigmoid (SIELU) which was implemented in the development of a Deep Learning (DL) model along with other hyper parameters for classification of unknown abiotic stress protein sequences from crops of Poaceae family. To develop this models, data pertaining to four different abiotic stress (namely, cold, drought, heat and salinity) responsive proteins of the crops belonging to poaceae family were retrieved from public domain. It was observed that efficiency of the DL models with our proposed novel SIELU activation function outperformed the models as compared to GeLU activation function, SVM and RF with 95.11%, 80.78%, 94.97%, and 81.69% accuracy for cold, drought, heat and salinity, respectively. Also, a web-based tool, named DeepAProt (http://login1.cabgrid.res.in:5500/) was developed using flask API, along with its mobile app. This server/App will provide researchers a convenient tool, which is rapid and economical in identification of proteins for abiotic stress management in crops Poaceae family, in endeavour of higher production for food security and combating hunger, ensuring UN SDG goal 2.0.

Aziz NA, Abd. Aziz A. Augmenting ECG Data with Multiple Filters for a Better Emotion Recognition System

A physiological-based emotion recognition system (ERS) with a unimodal approach such as an electrocardiogram (ECG) is not as popular compared to a multimodal approach. However, a single modality has the advantage of lower development and computational cost. Therefore, this study focuses on a unimodal ECG-based ERS. The ECG-based ERS has the potential to become the next mass-adopted consumer application due to the wide availability of wearable and mobile ECG devices in the market. Currently, ECG-inclusive affective datasets are limited, and many of the existing datasets have small sample sizes. Hence, ECG-based ERS studies are stunted by the lack of quality data. A novel multi-filtering augmentation technique is proposed here to increase the sample size of the ECG data. This technique augments the ECG signals by cleaning the data in different ways. Three small ECG datasets labelled according to emotion state are used in this study. The benefit of the proposed augmentation techniques is measured using the classification accuracy of five machine learning algorithms; k-nearest neighbours (KNN), support vector machine, decision tree, random forest and multilayer perceptron. The results show that with the proposed technique, there is a significant improvement in performance for all the datasets and classifiers. KNN classifier improved the most with the augmented data and the reported classification accuracies of over 90%.

Empirical Study of Autism Spectrum Disorder Diagnosis Using Facial Images by Improved Transfer Learning Approach

Autism spectrum disorder (ASD) is a neurological illness characterized by deficits in cognition, physical activities, and social skills. There is no specific medication to treat this illness; only early intervention can improve brain functionality. Since there is no medical test to identify ASD, a diagnosis might be challenging. In order to determine a diagnosis, doctors consider the child's behavior and developmental history. The human face can be used as a biomarker as it is one of the potential reflections of the brain and thus can be used as a simple and handy tool for early diagnosis. This study uses several deep convolutional neural network (CNN)-based transfer learning approaches to detect autistic children using the facial image. An empirical study is conducted to select the best optimizer and set of hyperparameters to achieve better prediction accuracy using the CNN model. After training and validating with the optimized setting, the modified Xception model demonstrates the best performance by achieving an accuracy of 95% on the test set, whereas the VGG19, ResNet50V2, MobileNetV2, and EfficientNetB0 achieved 86.5%, 94%, 92%, and 85.8%, accuracy, respectively. Our preliminary computational results demonstrate that our transfer learning approaches outperformed existing methods. Our modified model can be employed to assist doctors and practitioners in validating their initial screening to detect children with ASD disease.

A Virtual Sensing Concept for Nitrogen and Phosphorus Monitoring Using Machine Learning Techniques

Harmful cyanobacterial bloom (HCB) is problematic for drinking water treatment, and some of its strains can produce toxins that significantly affect human health. To better control eutrophication and HCB, catchment managers need to continuously keep track of nitrogen (N) and phosphorus (P) in the water bodies. However, the high-frequency monitoring of these water quality indicators is not economical. In these cases, machine learning techniques may serve as viable alternatives since they can learn directly from the available surrogate data. In the present work, a random forest, extremely randomized trees (ET), extreme gradient boosting, k-nearest neighbors, a light gradient boosting machine, and bagging regressor-based virtual sensors were used to predict N and P in two catchments with contrasting land uses. The effect of data scaling and missing value imputation were also assessed, while the Shapley additive explanations were used to rank feature importance. A specification book, sensitivity analysis, and best practices for developing virtual sensors are discussed. Results show that ET, MinMax scaler, and a multivariate imputer were the best predictive model, scaler, and imputer, respectively. The highest predictive performance, reported in terms of R², was 97% in the rural catchment and 82% in an urban catchment.

Skin cancer diagnosis based on deep transfer learning and sparrow search algorithm

Skin cancer affects the lives of millions of people every year, as it is considered the most popular form of cancer. In the USA alone, approximately three and a half million people are diagnosed with skin cancer annually. The survival rate diminishes steeply as the skin cancer progresses. Despite this, it is an expensive and difficult procedure to discover this cancer type in the early stages. In this study, a threshold-based automatic approach for skin cancer detection, classification, and segmentation utilizing a meta-heuristic optimizer named sparrow search algorithm (SpaSA) is proposed. Five U-Net models (i.e., U-Net, U-Net++, Attention U-Net, V-net, and Swin U-Net) with different configurations are utilized to perform the segmentation process. Besides this, the meta-heuristic SpaSA optimizer is used to perform the optimization of the hyperparameters using eight pre-trained CNN models (i.e., VGG16, VGG19, MobileNet, MobileNetV2, MobileNetV3Large, MobileNetV3Small, NASNetMobile, and NASNetLarge). The dataset is gathered from five public sources in which two types of datasets are generated (i.e., 2-classes and 10-classes). For the segmentation, concerning the “skin cancer segmentation and classification” dataset, the best reported scores by U-Net++ with DenseNet201 as a backbone architecture are 0.104, $$94.16\%$$ 94.16 % , $$91.39\%$$ 91.39 % , $$99.03\%$$ 99.03 % , $$96.08\%$$ 96.08 % , $$96.41\%$$ 96.41 % , $$77.19\%$$ 77.19 % , $$75.47\%$$ 75.47 % in terms of loss, accuracy, F1-score, AUC, IoU, dice, hinge, and squared hinge, respectively, while for the “PH2” dataset, the best reported scores by the Attention U-Net with DenseNet201 as backbone architecture are 0.137, $$94.75\%$$ 94.75 % , $$92.65\%$$ 92.65 % , $$92.56\%$$ 92.56 % , $$92.74\%$$ 92.74 % , $$96.20\%$$ 96.20 % , $$86.30\%$$ 86.30 % , $$92.65\%$$ 92.65 % , $$69.28\%$$ 69.28 % , and $$68.04\%$$ 68.04 % in terms of loss, accuracy, F1-score, precision, sensitivity, specificity, IoU, dice, hinge, and squared hinge, respectively. For the “ISIC 2019 and 2020 Melanoma” dataset, the best reported overall accuracy from the applied CNN experiments is $$98.27\%$$ 98.27 % by the MobileNet pre-trained model. Similarly, for the “Melanoma Classification (HAM10K)” dataset, the best reported overall accuracy from the applied CNN experiments is $$98.83\%$$ 98.83 % by the MobileNet pre-trained model. For the “skin diseases image” dataset, the best reported overall accuracy from the applied CNN experiments is $$85.87\%$$ 85.87 % by the MobileNetV2 pre-trained model. After computing the results, the suggested approach is compared with 13 related studies.

Accurate Numerical Treatment on a Stochastic SIR Epidemic Model with Optimal Control Strategy

In this paper, a numerical study has been undertaken on the susceptible-infected-recovered (SIR) epidemic model that encompasses the mechanisms of the evolution of disease transmission; a prophylactic vaccination strategy in the susceptible populations, depending on the infective individuals. We furnish numerical and graphical simulation combined with explicit series solutions of the proposed model using the New Iterative Method (NIM) and Modified New Iterative Method (MNIM). The analytic-numeric New Iterative Method failed to deliver accurate solution for the large time domain. A new reliable algorithm based on NIM, the coupling of the Laplace transforms, and the New Iterative method is called Modified New Iterative Method (MNIM) which is presented to enhance the validity domain of NIM techniques. The convergence analysis of the MNIM has also been illustrated. The simulation results show that the vaccination strategy can slow down the spread of the epidemic rapidly. Numerical results illustrate the excellent performance of the MNIM and show that the modified method is much more accurate than the NIM.

A Two-Step Data Normalization Approach for Improving Classification Accuracy in the Medical Diagnosis Domain

Data normalization is a data preprocessing task and one of the first to be performed during intellectual analysis, particularly in the case of tabular data. The importance of its implementation is determined by the need to reduce the sensitivity of the artificial intelligence model to the values of the features in the dataset to increase the studied model’s adequacy. This paper focuses on the problem of effectively preprocessing data to improve the accuracy of intellectual analysis in the case of performing medical diagnostic tasks. We developed a new two-step method for data normalization of numerical medical datasets. It is based on the possibility of considering both the interdependencies between the features of each observation from the dataset and their absolute values to improve the accuracy when performing medical data mining tasks. We describe and substantiate each step of the algorithmic implementation of the method. We also visualize the results of the proposed method. The proposed method was modeled using six different machine learning methods based on decision trees when performing binary and multiclass classification tasks. We used six real-world, freely available medical datasets with different numbers of vectors, attributes, and classes to conduct experiments. A comparison between the effectiveness of the developed method and that of five existing data normalization methods was carried out. It was experimentally established that the developed method increases the accuracy of the Decision Tree and Extra Trees Classifier by 1–5% in the case of performing the binary classification task and the accuracy of the Bagging, Decision Tree, and Extra Trees Classifier by 1–6% in the case of performing the multiclass classification task. Increasing the accuracy of these classifiers only by using the new data normalization method satisfies all the prerequisites for its application in practice when performing various medical data mining tasks.

A Modified Iterative Algorithm for Numerical Investigation of HIV Infection Dynamics

The human immunodeficiency virus (HIV) mainly attacks CD4+ T cells in the host. Chronic HIV infection gradually depletes the CD4+ T cell pool, compromising the host’s immunological reaction to invasive infections and ultimately leading to acquired immunodeficiency syndrome (AIDS). The goal of this study is not to provide a qualitative description of the rich dynamic characteristics of the HIV infection model of CD4+ T cells, but to produce accurate analytical solutions to the model using the modified iterative approach. In this research, a new efficient method using the new iterative method (NIM), the coupling of the standard NIM and Laplace transform, called the modified new iterative method (MNIM), has been introduced to resolve the HIV infection model as a class of system of ordinary differential equations (ODEs). A nonlinear HIV infection dynamics model is adopted as an instance to elucidate the identification process and the solution process of MNIM, only two iterations lead to ideal results. In addition, the model has also been solved using NIM and the fourth order Runge–Kutta (RK4) method. The results indicate that the solutions by MNIM match with those of RK4 method to a minimum of eight decimal places, whereas NIM solutions are not accurate enough. Numerical comparisons between the MNIM, NIM, the classical RK4 and other methods reveal that the modified technique has potential as a tool for the nonlinear systems of ODEs.

Sensor Screening Methodology for Virtually Sensing Transmission Input Loads of a Wind Turbine Using Machine Learning Techniques and Drivetrain Simulations

The ongoing trend of building larger wind turbines (WT) to reach greater economies of scale is contributing to the reduction in cost of wind energy, as well as the increase in WT drivetrain input loads into uncharted territories. The resulting intensification of the load situation within the WT gearbox motivates the need to monitor WT transmission input loads. However, due to the high costs of direct measurement solutions, more economical solutions, such as virtual sensing of transmission input loads using stationary sensors mounted on the gearbox housing or other drivetrain locations, are of interest. As the number, type, and location of sensors needed for a virtual sensing solutions can vary considerably in cost, in this investigation, we aimed to identify optimal sensor locations for virtually sensing WT 6-degree of freedom (6-DOF) transmission input loads. Random forest (RF) models were designed and applied to a dataset containing simulated operational data of a Vestas V52 WT multibody simulation model undergoing simulated wind fields. The dataset contained the 6-DOF transmission input loads and signals from potential sensor locations covering deformations, misalignments, and rotational speeds at various drivetrain locations. The RF models were used to identify the sensor locations with the highest impact on accuracy of virtual load sensing following a known statistical test in order to prioritize and reduce the number of needed input signals. The performance of the models was assessed before and after reducing the number of input signals required. By allowing for a screening of sensors prior to real-world tests, the results demonstrate the high promise of the proposed method for optimizing the cost of future virtual WT transmission load sensors.

A Comparative Analysis on Suicidal Ideation Detection Using NLP, Machine, and Deep Learning

Social networks are essential resources to obtain information about people’s opinions and feelings towards various issues as they share their views with their friends and family. Suicidal ideation detection via online social network analysis has emerged as an essential research topic with significant difficulties in the fields of NLP and psychology in recent years. With the proper exploitation of the information in social media, the complicated early symptoms of suicidal ideations can be discovered and hence, it can save many lives. This study offers a comparative analysis of multiple machine learning and deep learning models to identify suicidal thoughts from the social media platform Twitter. The principal purpose of our research is to achieve better model performance than prior research works to recognize early indications with high accuracy and avoid suicide attempts. We applied text pre-processing and feature extraction approaches such as CountVectorizer and word embedding, and trained several machine learning and deep learning models for such a goal. Experiments were conducted on a dataset of 49,178 instances retrieved from live tweets by 18 suicidal and non-suicidal keywords using Python Tweepy API. Our experimental findings reveal that the RF model can achieve the highest classification score among machine learning algorithms, with an accuracy of 93% and an F1 score of 0.92. However, training the deep learning classifiers with word embedding increases the performance of ML models, where the BiLSTM model reaches an accuracy of 93.6% and a 0.93 F1 score.

A Multi-Step Time-Series Clustering-Based Seq2Seq LSTM Learning for a Single Household Electricity Load Forecasting

The deep learning (DL) approaches in smart grid (SG) describes the possibility of shifting the energy industry into a modern era of reliable and sustainable energy networks. This paper proposes a time-series clustering framework with multi-step time-series sequence to sequence (Seq2Seq) long short-term memory (LSTM) load forecasting strategy for households. Specifically, we investigate a clustering-based Seq2Seq LSTM electricity load forecasting model to undertake an energy load forecasting problem, where information input to the model contains individual appliances and aggregate energy as historical data of households. The original dataset is preprocessed, and forwarded to a multi-step time-series learning model which reduces the training time and guarantees convergence for energy forecasting. Furthermore, simulation results show the accuracy performance of the proposed model by validation and testing cluster data, which shows a promising potential of the proposed predictive model.

Machine-Learning-Based Disease Diagnosis: A Comprehensive Review

Globally, there is a substantial unmet need to diagnose various diseases effectively. The complexity of the different disease mechanisms and underlying symptoms of the patient population presents massive challenges in developing the early diagnosis tool and effective treatment. Machine learning (ML), an area of artificial intelligence (AI), enables researchers, physicians, and patients to solve some of these issues. Based on relevant research, this review explains how machine learning (ML) is being used to help in the early identification of numerous diseases. Initially, a bibliometric analysis of the publication is carried out using data from the Scopus and Web of Science (WOS) databases. The bibliometric study of 1216 publications was undertaken to determine the most prolific authors, nations, organizations, and most cited articles. The review then summarizes the most recent trends and approaches in machine-learning-based disease diagnosis (MLBDD), considering the following factors: algorithm, disease types, data type, application, and evaluation metrics. Finally, in this paper, we highlight key results and provides insight into future trends and opportunities in the MLBDD area.

A Machine Learning Based Model for Energy Usage Peak Prediction in Smart Farms

Context: Energy utilization is one of the most closely related factors affecting many areas of the smart farm, plant growth, crop production, device automation, and energy supply to the same degree. Recently, 4th industrial revolution technologies such as IoT, artificial intelligence, and big data have been widely used in smart farm environments to efficiently use energy and control smart farms’ conditions. In particular, machine learning technologies with big data analysis are actively used as one of the most potent prediction methods supporting energy use in the smart farm. Purpose: This study proposes a machine learning-based prediction model for peak energy use by analyzing energy-related data collected from various environmental and growth devices in a smart paprika farm of the Jeonnam Agricultural Research and Extension Service in South Korea between 2019 and 2021. Scientific method: To find out the most optimized prediction model, comparative evaluation tests are performed using representative ML algorithms such as artificial neural network, support vector regression, random forest, K-nearest neighbors, extreme gradient boosting and gradient boosting machine, and time series algorithm ARIMA with binary classification for a different number of input features. Validate: This article can provide an effective and viable way for smart farm managers or greenhouse farmers who can better manage the problem of agricultural energy economically and environmentally. Therefore, we hope that the recommended ML method will help improve the smart farm’s energy use or their energy policies in various fields related to agricultural energy. Conclusion: The seven performance metrics including R-squared, root mean squared error, and mean absolute error, are associated with these two algorithms. It is concluded that the RF-based model is more successful than in the pre-others diction accuracy of 92%. Therefore, the proposed model may be contributed to the development of various applications for environment energy usage in a smart farm, such as a notification service for energy usage peak time or an energy usage control for each device.

Traffic Flow Prediction for Smart Traffic Lights Using Machine Learning Algorithms

Nowadays, many cities have problems with traffic congestion at certain peak hours, which produces more pollution, noise and stress for citizens. Neural networks (NN) and machine-learning (ML) approaches are increasingly used to solve real-world problems, overcoming analytical and statistical methods, due to their ability to deal with dynamic behavior over time and with a large number of parameters in massive data. In this paper, machine-learning (ML) and deep-learning (DL) algorithms are proposed for predicting traffic flow at an intersection, thus laying the groundwork for adaptive traffic control, either by remote control of traffic lights or by applying an algorithm that adjusts the timing according to the predicted flow. Therefore, this work only focuses on traffic flow prediction. Two public datasets are used to train, validate and test the proposed ML and DL models. The first one contains the number of vehicles sampled every five minutes at six intersections for 56 days using different sensors. For this research, four of the six intersections are used to train the ML and DL models. The Multilayer Perceptron Neural Network (MLP-NN) obtained better results (R-Squared and EV score of 0.93) and took less training time, followed closely by Gradient Boosting then Recurrent Neural Networks (RNNs), with good metrics results but the longer training time, and finally Random Forest, Linear Regression and Stochastic Gradient. All ML and DL algorithms scored good performance metrics, indicating that they are feasible for implementation on smart traffic light controllers.

‘Exploring socioeconomic status as a global determinant of COVID-19 prevalence, using statistical, exploratory data analytic, and supervised machine learning techniques.’ (Preprint)

Background

The COVID-19 pandemic represents the most unprecedented global challenge in recent times. As the global community attempts to manage the pandemic in the long term, it is pivotal to understand what factors drive prevalence rates and to predict the future trajectory of the virus.

Objective

This study had 2 objectives. First, it tested the statistical relationship between socioeconomic status and COVID-19 prevalence. Second, it used machine learning techniques to predict cumulative COVID-19 cases in a multicountry sample of 182 countries. Taken together, these objectives will shed light on socioeconomic status as a global risk factor of the COVID-19 pandemic.

Methods

This research used exploratory data analysis and supervised machine learning methods. Exploratory analysis included variable distribution, variable correlations, and outlier detection. Following this, the following 3 supervised regression techniques were applied: linear regression, random forest, and adaptive boosting (AdaBoost). Results were evaluated using k-fold cross-validation and subsequently compared to analyze algorithmic suitability. The analysis involved 2 models. First, the algorithms were trained to predict 2021 COVID-19 prevalence using only 2020 reported case data. Following this, socioeconomic indicators were added as features and the algorithms were trained again. The Human Development Index (HDI) metrics of life expectancy, mean years of schooling, expected years of schooling, and gross national income were used to approximate socioeconomic status.

Results

All variables correlated positively with the 2021 COVID-19 prevalence, with R² values ranging from 0.55 to 0.85. Using socioeconomic indicators, COVID-19 prevalence was predicted with a reasonable degree of accuracy. Using 2020 reported case rates as a lone predictor to predict 2021 prevalence rates, the average predictive accuracy of the algorithms was low (R²=0.543). When socioeconomic indicators were added alongside 2020 prevalence rates as features, the average predictive performance improved considerably (R²=0.721) and all error statistics decreased. Thus, adding socioeconomic indicators alongside 2020 reported case data optimized the prediction of COVID-19 prevalence to a considerable degree. Linear regression was the strongest learner with R²=0.693 on the first model and R²=0.763 on the second model, followed by random forest (0.481 and 0.722) and AdaBoost (0.454 and 0.679). Following this, the second model was retrained using a selection of additional COVID-19 risk factors (population density, median age, and vaccination uptake) instead of the HDI metrics. However, average accuracy dropped to 0.649, which highlights the value of socioeconomic status as a predictor of COVID-19 cases in the chosen sample.

Conclusions

The results show that socioeconomic status is an important variable to consider in future epidemiological modeling, and highlights the reality of the COVID-19 pandemic as a social phenomenon and a health care phenomenon. This paper also puts forward new considerations about the application of statistical and machine learning techniques to understand and combat the COVID-19 pandemic.

DeepSense: A Physics-Guided Deep Learning Paradigm for Anomaly Detection in Soil Gas Data at Geologic CO2 Storage Sites

Driven by the collection of enormous amounts of streaming data from sensors, and with the emergence of the internet of things, the need for developing robust detection techniques to identify data anomalies has increased recently. The algorithms for anomaly detection are required to be selected based on the type of data. In this study, we propose a predictive anomaly detection technique, DeepSense, which is applied to soil gas concentration data acquired from sensors being used for environmental characterization at a prospective CO₂ storage site in Queensland, Australia. DeepSense takes advantage of deep-learning algorithms as its predictor module and uses a process-based soil gas method as the basis of its anomaly detector module. The proposed predictor framework leverages the power of convolutional neural network algorithms for feature extraction and simultaneously captures the long-term temporal dependency through long short-term memory algorithms. The proposed process-based anomaly detection method is a cost-effective alternative to the conventional concentration-based soil gas methodologies which rely on long-term baseline surveys for defining the threshold level. The results indicate that the proposed framework performs well in diagnosing anomalous data in soil gas concentration data streams. The robustness and efficacy of the DeepSense were verified against data sets acquired from different monitoring stations of the storage site.

Prediction of Hemorrhagic Transformation after Ischemic Stroke Using Machine Learning

Hemorrhagic transformation (HT) is one of the leading causes of a poor prognostic marker after acute ischemic stroke (AIS). We compared the performances of the several machine learning (ML) algorithms to predict HT after AIS using only structured data. A total of 2028 patients with AIS, who were admitted within seven days of symptoms onset, were included in this analysis. HT was defined based on the criteria of the European Co-operative Acute Stroke Study-II trial. The whole dataset was randomly divided into a training and a test dataset with a 7:3 ratio. Binary logistic regression, support vector machine, extreme gradient boosting, and artificial neural network (ANN) algorithms were used to assess the performance of predicting the HT occurrence after AIS. Five-fold cross validation and a grid search technique were used to optimize the hyperparameters of each ML model, which had its performance measured by the area under the receiver operating characteristic (AUROC) curve. Among the included AIS patients, the mean age and number of male subjects were 69.6 years and 1183 (58.3%), respectively. HT was observed in 318 subjects (15.7%). There were no significant differences in corresponding variables between the training and test dataset. Among all the ML algorithms, the ANN algorithm showed the best performance in terms of predicting the occurrence of HT in our dataset (0.844). Feature scaling including standardization and normalization, and the resampling strategy showed no additional improvement of the ANN's performance. The ANN-based prediction of HT after AIS showed better performance than the conventional ML algorithms. Deep learning may be used to predict important outcomes for structured data-based prediction.