Analysis of input set characteristics and variances on k-fold cross validation for a Recurrent Neural Network model on waste disposal rate estimation

Improving the estimation of rice above-ground biomass based on spatio-temporal UAV imagery and phenological stages

Introduction

Unmanned aerial vehicles (UAVs) equipped with visible and multispectral cameras provide reliable and efficient methods for remote crop monitoring and above-ground biomass (AGB) estimation in rice fields. However, existing research predominantly focuses on AGB estimation based on canopy spectral features or by incorporating plant height (PH) as a parameter. Insufficient consideration has been given to the spatial structure and the phenological stages of rice in these studies. In this study, a novel method was introduced by fully considering the three-dimensional growth dynamics of rice, integrating both horizontal (canopy cover, CC) and vertical (PH) aspects of canopy development, and accounting for the growing days of rice.

Methods

To investigate the synergistic effects of combining spectral, spatial and temporal parameters, both small-scale plot experiments and large-scale field testing were conducted in Jiangsu Province, China from 2021 to 2022. Twenty vegetation indices (VIs) were used as spectral features, PH and CC as spatial parameters, and days after transplanting (DAT) as a temporal parameter. AGB estimation models were built with five regression methods (MSR, ENet, PLSR, RF and SVR), using the derived data from six feature combinations (VIs, PH+CC, PH+CC+DAT, VIs+PH +CC, VIs+DAT, VIs+PH+CC+DAT).

Results

The results showed a strong correlation between extracted and ground-measured PH (R2 = 0.89, RMSE=5.08 cm). Furthermore, VIs, PH and CC exhibit strong correlations with AGB during the mid-tillering to flowering stages. The optimal AGB estimation results during the mid-tillering to flowering stages on plot data were from the PLSR model with VIs and DAT as inputs (R 2 = 0.88, RMSE=1111kg/ha, NRMSE=9.76%), and with VIs, PH, CC, and DAT all as inputs (R 2 = 0.88, RMSE=1131 kg/ha, NRMSE=9.94%). For the field sampling data, the ENet model combined with different feature inputs had the best estimation results (%error=0.6%-13.5%), demonstrating excellent practical applicability.

Discussion

Model evaluation and feature importance ranking demonstrated that augmenting VIs with temporal and spatial parameters significantly enhanced the AGB estimation accuracy. In summary, the fusion of spectral and spatio-temporal features enhanced the actual physical significance of the AGB estimation models and showed great potential for accurate rice AGB estimation during the main phenological stages.

Prophet time series modeling of waste disposal rates in four North American cities

In this study, three different univariate municipal solid waste (MSW) disposal rate forecast models (SARIMA, Holt-Winters, Prophet) were examined using different testing periods in four North American cities with different socioeconomic conditions. A review of the literature suggests that the selected models are able to handle seasonality in a time series; however, their ability to handle outliers is not well understood. The Prophet model generally outperformed the Holt-Winters model and the SARIMA model. The MAPE and R2 of the Prophet model during pre-COVID-19 were 4.3-22.2% and 0.71-0.93, respectively. All three models showed satisfactory predictive results, especially during the pre-COVID-19 testing period. COVID-19 lockdowns and the associated regulatory measures appear to have affected MSW disposal behaviors, and all the univariate models failed to fully capture the abrupt changes in waste disposal behaviors. Modeling errors were largely attributed to data noise in seasonality and the unprecedented event of COVID-19 lockdowns. Overall, the modeling errors of the Prophet model were evenly distributed, with minimum modeling biases. The Prophet model also appeared to be versatile and successfully captured MSW disposal rates from 3000 to 39,000 tons/month. The study highlights the potential benefits of the use of univariate models in waste forecast.

Spectral analysis and Bi-LSTM deep network-based approach in detection of mild cognitive impairment from electroencephalography signals

Mild cognitive impairment (MCI) is a neuropsychological syndrome that is characterized by cognitive impairments. It typically affects adults 60 years of age and older. It is a noticeable decline in the cognitive function of the patient, and if left untreated it gets converted to Alzheimer's disease (AD). For that reason, early diagnosis of MCI is important as it slows down the conversion of the disease to AD. Early and accurate diagnosis of MCI requires recognition of the clinical characteristics of the disease, extensive testing, and long-term observations. These observations and tests can be subjective, expensive, incomplete, or inaccurate. Electroencephalography (EEG) is a powerful choice for the diagnosis of diseases with its advantages such as being non-invasive, based on findings, less costly, and getting results in a short time. In this study, a new EEG-based model is developed which can effectively detect MCI patients with higher accuracy. For this purpose, a dataset consisting of EEG signals recorded from a total of 34 subjects, 18 of whom were MCI and 16 control groups was used, and their ages ranged from 40 to 77. To conduct the experiment, the EEG signals were denoised using Multiscale Principal Component Analysis (MSPCA), and to increase the size of the dataset Data Augmentation (DA) method was performed. The tenfold cross-validation method was used to validate the model, moreover, the power spectral density (PSD) of the EEG signals was extracted from the EEG signals using three spectral analysis methods, the periodogram, welch, and multitaper. The PSD graphs of the EEG signals showed signal differences between the subjects of control and the MCI group, indicating that the signal power of MCI patients is lower compared to control groups. To classify the subjects, one of the best classifiers of deep learning algorithms called the Bi-directional long-short-term-memory (Bi-LSTM) was used, and several machine learning algorithms, such as decision tree (DT), support vector machine (SVM), and k-nearest neighbor (KNN). These algorithms were trained and tested using the extracted feature vectors from the control and the MCI groups. Additionally, the values of the coefficient matrix of those algorithms were compared and evaluated with the performance evaluation matrix to determine which one performed the best overall. According to the experimental results, the proposed deep learning model of multitaper spectral analysis approach with Bi-LSTM deep learning algorithm attained the highest number of correctly classified samples for diagnosing MCI patients and achieved a remarkable accuracy compared to the other proposed models. The achieved classification results of the deep learning model are reported to be 98.97% accuracy, 98.34% sensitivity, 99.67% specificity, 99.70% precision, 99.02% f1 score, and 97.94% Matthews correlation coefficient (MCC).

Precision forecasting of spray-dry desulfurization using Gaussian noise data augmentation and k-fold cross-validation optimized neural computing

Perceptron models have become integral tools for pattern recognition and classification problems in engineering fields. This study envisioned implementing artificial neural networks to forecast the performance of a mini-spray dryer for desulfurization activities. This work adopted k-fold cross-validation, a rigorous technique that evaluates model performance across multiple data segments. Several ANN models (21) were trained on data obtained from sulfation conditions, including sulfation temperature (120 °C-200 °C), slurry pH (4-12), stoichiometric ratio (0.5-2.5), slurry solid concentration (6%-14%) as the feed input and sulfur capture as the response. Three hundred synthetic datasets generated using the Gaussian noise data augmentation underwent a 10-fold cross-validation process before simulation on neural networks triggered by the logsig and tansig activation functions. The computation accuracy was further evaluated by altering the number of hidden cells from 2 to 10. The ANN architectures were assessed using statistical metrics such as mean square error (MSE), root mean square error (RMSE), mean absolute percentage error (MAPE), and the coefficient of determination (R2) techniques. Overall, error estimation suggests cross-validation and data augmentation are critical in efficient neural network generalization. The logsig function trained with 10 hidden cells presented closer data articulation when mapped onto actual values.

A weighted distance-based dynamic ensemble regression framework for gastric cancer survival time prediction

Accurate prediction of gastric cancer patient survival time is essential for clinical decision-making. However, unified static models lack specificity and flexibility in predictions owing to the varying survival outcomes among gastric cancer patients. We address these problems by using an ensemble learning approach and adaptively assigning greater weights to similar patients to make more targeted predictions when predicting an individual's survival time. We treat these problems as regression problems and introduce a weighted dynamic ensemble regression framework. To better identify similar patients, we devise a method to measure patient similarity, considering the diverse impacts of features. Subsequently, we use this measure to design both a weighted K-means clustering method and a fuzzy K-means sampling technique to group patients and train corresponding base regressors. To achieve more targeted predictions, we calculate the weight of each base regressor based on the similarity between the patient to be predicted and the patient clusters, culminating in the integration of the results. The model is validated on a dataset of 7791 patients, outperforming other models in terms of three evaluation metrics, namely, the root mean square error, mean absolute error, and the coefficient of determination. The weighted dynamic ensemble regression strategy can improve the baseline model by 1.75%, 2.12%, and 13.45% in terms of the three respective metrics while also mitigating the imbalanced survival time distribution issue. This enhanced performance has been statistically validated, even when tested on six public datasets with different sizes. By considering feature variations, patients with distinct survival profiles can be effectively differentiated, and the model predictive performance can be enhanced. The results generated by our proposed model can be invaluable in guiding decisions related to treatment plans and resource allocation. Furthermore, the model has the potential for broader applications in prognosis for other types of cancers or similar regression problems in various domains.

Enhancement of isoprene production in engineered Synechococcus elongatus UTEX 2973 by metabolic pathway inhibition and machine learning-based optimization strategy

An engineered Synechococcus elongatus UTEX 2973-IspS.IDI is used to enhance isoprene production through geranyl diphosphate synthase (CrtE) inhibition and process parameters (light intensity, NaHCO3 and growth temperature) optimization approach. A cumulative isoprene production of 1.21 mg/gDCW was achieved with productivity of 12.6 μg/gDCW/h in culture supplemented with 20 μg/mL alendronate. This inhibition strategy improvises the cumulative isoprene production 5.76-fold in presence of alendronate. The maximum cumulative production of isoprene is observed to be 5.22 and 6.20 mg/gDCW (54.4 and 64.6 μg/gDCW/h) at statistical and artificial neural network genetic algorithm (ANN-GA) optimized conditions, respectively. The overall increase of isoprene production is found to be 29.52-fold using an integrated approach of inhibition and ANN-GA optimization in comparison to unoptimized cultures without alendronate. This study reveals that alendronate use as a potential inhibitor and machine learning based optimization is a better approach in comparison to statistical optimization to enhance the isoprene production.

Diagnostic Value of Immunological Biomarkers in Children with Asthmatic Bronchitis and Asthma

Background and Objectives: This study aimed to investigate the diagnostic value of immunological biomarkers in children with asthmatic bronchitis and asthma and to develop a machine learning (ML) model for rapid differential diagnosis of these two diseases. Materials and Methods: Immunological biomarkers in peripheral blood were detected using flow cytometry and immunoturbidimetry. The importance of characteristic variables was ranked and screened using random forest and extra trees algorithms. Models were constructed and tested using the Scikit-learn ML library. K-fold cross-validation and Brier scores were used to evaluate and screen models. Results: Children with asthmatic bronchitis and asthma exhibit distinct degrees of immune dysregulation characterized by divergent patterns of humoral and cellular immune responses. CD8+ T cells and B cells were more dominant in differentiating the two diseases among many immunological biomarkers. Random forest showed a comprehensive high performance compared with other models in learning and training the dataset of immunological biomarkers. Conclusions: This study developed a prediction model for early differential diagnosis of asthmatic bronchitis and asthma using immunological biomarkers. Evaluation of the immune status of patients may provide additional clinical information for those children transforming from asthmatic bronchitis to asthma under recurrent attacks.

A cross-jurisdictional comparison on residential waste collection rates during earlier waves of COVID-19

There is currently a lack of studies on residential waste collection during COVID-19 in North America. SARIMA models were developed to predict residential waste collection rates (RWCR) across four North American jurisdictions before and during the pandemic. Unlike waste disposal rates, RWCR is relatively less sensitive to the changes in COVID-19 regulatory policies and administrative measures, making RWCR more appropriate for cross-jurisdictional comparisons. It is hypothesized that the use of RWCR in forecasting models will help us to better understand the residential waste generation behaviors in North America. Both SARIMA models performed satisfactorily in predicting Regina's RWCR. The SARIMA D_CV model's performance is noticeably better during COVID-19, with a 15.7% lower RMSE than that of the benchmark model (SARIMA B_CV). The skewness of overprediction ratios was noticeably different between jurisdictions, and modeling errors were generally lower in less populated cities. Conflicting behavioral changes might have altered the residential waste generation characteristics and recycling behaviors differently across the jurisdictions. Overall, SARIMA D_CV performed better in the Canadian jurisdiction than in U.S. jurisdictions, likely due to the model's bias on a less variable input dataset. The use of RWCR in forecasting models helps us to better understand the residential waste generation behaviors in North America and better prepare us for a future global pandemic.

Spatiotemporal analysis and predicting rainfall trends in a tropical monsoon-dominated country using MAKESENS and machine learning techniques

Spatiotemporal rainfall trend analysis as an indicator of climatic change provides critical information for improved water resource planning. However, the spatiotemporal changing behavior of rainfall is much less understood in a tropical monsoon-dominated country like Bangladesh. To this end, this research aims to analyze spatiotemporal variations in rainfall for the period 1980-2020 over Bangladesh at seasonal and monthly scales using MAKESENS, the Pettitt test, and innovative trend analysis. Multilayer Perception (MLP) neural network was used to predict the next 8 years' rainfall changes nationally in Bangladesh. To investigate the spatial pattern of rainfall trends, the inverse distance weighting model was adopted within the ArcGIS environment. Results show that mean annual rainfall is 2432.6 mm, of which 57.6% was recorded from July to August. The Mann-Kendall trend test reveals that 77% of stations are declining, and 23% have a rising trend in the monthly rainfall. More than 80% of stations face a declining trend from November to March and August. There is a declining trend for seasonal rainfall at 82% of stations during the pre-monsoon, 75% during the monsoon, and 100% during the post-monsoon. A significant decline trend was identified in the north-center during the pre-monsoon, the northern part during the monsoon, and the southern and northwestern portions during the post-monsoon season. Predicted rainfall by MLP till 2030 suggests that there will be little rain from November to February, and the maximum fluctuating rainfall will occur in 2025 and 2027-2029. The ECMWF ERA5 reanalysis data findings suggested that changing rainfall patterns in Bangladesh may have been driven by rising or reducing convective precipitation rates, low cloud cover, and inadequate vertically integrated moisture divergence. Given the shortage of water resources and the anticipated rise in water demand, the study's findings have some implications for managing water resources in Bangladesh.

Self-attention (SA) temporal convolutional network (SATCN)-long short-term memory neural network (SATCN-LSTM): an advanced python code for predicting groundwater level

Groundwater level prediction is important for effective water management. Accurately predicting groundwater levels allows decision-makers to make informed decisions about water allocation, groundwater abstraction rates, and groundwater recharge strategies. This study presents a novel model, the self-attention (SA) temporal convolutional network (SATCN)-long short-term memory neural network (SATCN-LSTM), for groundwater level prediction. The SATCN-LSTM model combines the advantages of the SATCN and LSTM models to overcome the limitations of the LSTM model. By utilizing skip connections and self-attention mechanisms, the SATCN model addresses the vanishing gradient problem, identifies relevant data, and captures both short- and long-term dependencies in time series data. By demonstrating the improved performance of the SATCN-LSTM model in terms of mean absolute error and root mean square error (RMSE), and by comparing these results with those reported in previous papers, we have highlighted the advancements and contributions of the proposed model. By improving prediction accuracy, the SATCN-LSTM model enables decision-makers to make informed choices regarding water allocation, groundwater abstraction rates, and drought preparedness. The SATCN-LSTM model contributes to the sustainable and efficient use of groundwater resources by providing reliable information for decision-making processes. The SATCN-LSTM model combines the temporal convolutional network (TCN) architecture with LSTM. TCN is known for its ability to capture short-term dependencies in time series data, while LSTM is effective at capturing long-term dependencies. By integrating both architectures, the SATCN-LSTM model can capture the complex temporal relationships at different scales, leading to improved prediction accuracy. Meteorological data were used to predict GWL. The SATCN-LSTM model outperformed the other models. The SATCN-LSTM model had the lowest mean absolute error (MAE) of 0.09, followed by the self-attention (SA) temporal convolutional network (SATCN) model with an MAE of 0.12. The SALSTM model had an MAE of 0.16, while the TCN-LSTM, temporal convolutional network (TCN), and LSTM models had MAEs of 0.17, 0.22, and 0.23, respectively. The SATCN-LSTM model had the lowest root mean square error of 0.14, followed by SATCN with an RMSE of 0.15. The study results indicated that the SATCN-LSTM model was a robust tool for predicting groundwater level.

Environmental impact assessment of multi-source solid waste based on a life cycle assessment, principal component analysis, and random forest algorithm

As a national pilot city for solid waste disposal and resource reuse, Dongguan in Guangdong Province aims to vigorously promote the high-value utilization of solid waste and contribute to the sustainable development of the Greater Bay Area. In this study, life cycle assessment (LCA) coupled with principal component analysis (PCA) and the random forest (RF) algorithm was applied to assess the environmental impact of multi-source solid waste disposal technologies to guide the environmental protection direction. In order to improve the technical efficiency and reduce pollution emissions, some advanced technologies including carbothermal reduction‒oxygen-enriched side blowing, directional depolymerization‒flocculation demulsification, anaerobic digestion and incineration power generation, were applied for treating inorganic waste, organic waste, kitchen waste and household waste in the park. Based on the improved techniques, we proposed a cyclic model for multi-source solid waste disposal. Results of the combined LCA-PCA-RF calculation indicated that the key environmental load type was human toxicity potential (HTP), came from the technical units of carbothermal reduction and oxygen-enriched side blowing. Compared to the improved one, the cyclic model was proved to reduce material and energy inputs by 66%-85% and the pollution emissions by 15%-88%. To sum up, the environmental impact assessment and systematic comparison suggest a cyclic mode for multi-source solid waste treatments in the park, which could be promoted and contributed to the green and low-carbon development of the city.

Unlocking the potential of transesterification catalysts for biodiesel production through machine learning approach

The growing demand for fossil fuels has motivated the search for a renewable energy source, and biodiesel has emerged as a promising and environmentally friendly alternative. In this study, machine learning techniques were employed to predict the biodiesel yield from transesterification processes using three different catalysts: homogeneous, heterogeneous, and enzyme. Extreme gradient boosting algorithms showed the highest accuracy in predictions, with a coefficient of determination accuracy of nearly 0.98, as determined through a 10-fold cross-validation of the input data. The results indicated that linoleic acid, behenic acid, and reaction time were the most crucial factors affecting biodiesel yield predictions for homogeneous, heterogeneous, and enzyme catalysts, respectively. This research provides insights into the individual and combined effects of key factors on transesterification catalysts, contributing to a deeper understanding of the system.

Serum Raman spectroscopy combined with convolutional neural network for rapid diagnosis of HER2-positive and triple-negative breast cancer

Breast cancer is common in women, and its number of patients ranks first among female malignant tumors. Breast cancer is highly heterogeneous, and different types of breast cancer have different biological behaviors and prognoses. Therefore, identifying the different types of breast cancer is of great help in formulating individualized treatment plans. Based on serum Raman spectroscopy and deep learning algorithms, we propose a fast and low-cost diagnosis method for screening triple-negative breast cancer, human epidermal growth factor receptor 2 (HER2)-positive breast cancer, and healthy controls. We collected 75 serum samples in this study, including 23 triple-negative breast cancers, 22 HER2-positive breast cancers, and 30 healthy controls. Using the preprocessed Raman spectra as the input of deep learning, three deep learning models, neural network language model (NNLM), bidirectional long-short-term memory network (BiLSTM), and convolutional neural network (CNN), were established, and the accuracy rates of the three models were 87.78%, 90.37%, and 91.11%, respectively. The experimental results demonstrate the feasibility of serum Raman spectroscopy combined with deep learning algorithms to diagnose breast cancer, which can be used as an effective auxiliary diagnosis method for breast cancer.

Workers’ Opinions on Using the Internet of Things to Enhance the Performance of the Olive Oil Industry: A Machine Learning Approach

Today’s global food supply chains are highly dispersed and complex. The adoption and effective utilization of information technology are likely to increase the efficiency of companies. Because of the broad variety of sensors that are currently accessible, the possibilities for Internet of Things (IoT) applications in the olive oil industry are almost limitless. Although previous studies have investigated the impact of the IoT on the performance of industries, this issue has yet to be explored in the olive oil industry. In this study we aimed to develop a new model to investigate the factors influencing supply chain improvement in olive oil companies. The model was used to evaluate the relationship between supply chain improvement and olive oil companies’ performance. Demand planning, manufacturing, transportation, customer service, warehousing, and inventory management were the main factors incorporated into the proposed model. Self-organizing map (SOM) clustering and decision trees were employed in the development of the method. The data were collected from respondents with knowledge related to integrating new technologies into the industry. The results demonstrated that IoT implementation in olive oil companies significantly improved their performance. Moreover, it was found that there was a positive relationship between supply chain improvements via IoT implementation in olive oil companies and their performance.