Elastic Net Algorithm Research Articles

Brain encoding during perceived control as a prospective predictor of improvement in quality of life.

Perceived control is strongly related to mental health and well-being. Specifically, lack of perceived control has been associated with learned helplessness and stress-related disorders, such as depression and anxiety. However, it is unknown whether brain activation to control and its protective effect against stress can predict changes in quality of life. To address this gap, we examined the neural underpinning of controllability in healthy females (N=40) performing the Value of Control task in an fMRI scanner. Quality of life and perceived stress were assessed at baseline and 6-month follow-up. Increased brain activation for control was found within the putamen, insula, thalamus, mid-cingulate, dorsolateral prefrontal cortex, motor cortex, and cerebellum. In contrast, increased brain activation for lack of control was found within the posterior cingulate and prefrontal cortices. In an exploratory analysis, an elastic-net algorithm was used to identify brain predictors of quality of life 6 months later. The right putamen's activation to control was selected as the best prospective predictor of improvement in life enjoyment and satisfaction and this association was mediated by changes in perceived stress. Our findings suggest that neural responsiveness to control may have utility as a potential marker of quality of life and resilience to adversity.

Objective quantification of sound sensory attributes in side-by-side vehicles using multiple linear regression models

The evaluation of sound quality is a pivotal area of research within audio and acoustics. The sound quality evaluation methods commonly used include both objective and subjective, the latter being time-consuming and costly as they rely on listening tests. This research work aims to investigate the use of predictive sound quality models as a way to objectively assess the Desire-to-buy of side-by-side vehicles, in a more efficient, faster, and less costly way than conventional methods. Multiple linear regression algorithms were used to validate the objective models derived from objective physical metrics and perceptual psycho-physical metrics. The sensory profile objective models reported in this paper were constructed using parsimonious linear Lasso and Elastic-net algorithms. Our results show that linear objective models effectively account for each of the perceptual attributes of the sensory profiles and the Desire-to-buy, while only requiring a few physical and psychophysical metrics.

Predictive analysis of breast cancer metastasis and identification of genetic markers using machine learning.

4 Background: The study devises a framework integrating machine learning (ML) paradigms with explainable artificial intelligence (XAI) to prognosticate the metastatic trajectory of breast cancer (BC) and delineate critical genomic indicators pertinent to metastasis. Methods: An examination was conducted on 98 initial BC specimens, which included 34 instances evolving into distant metastasis within a quintennial monitoring phase and 44 instances evincing no recurrence for a minimum pentad post-diagnosis. Genomic datasets underwent rigorous biostatistical scrutiny, followed by the implementation of an elastic net algorithm for feature discernment, thereby constraining the scope to a salient subset of genomic markers implicated in BC metastasis. An ensemble of advanced predictive models encompassing Light Gradient Boosting Machine (LightGBM), Categorical Boosting (CatBoost), Extreme Gradient Boosting (XGBoost), Gradient Boosting Trees (GBT), and Adaptive Boosting (AdaBoost) was deployed. Model efficacy was gauged through metrics such as accuracy, F1 score, precision, recall, the Area Under the Receiver Operating Characteristic Curve (AUC), and the Brier score. To elucidate the reasoning behind the ML predictions and to navigate the opacity inherent in such models, a SHapley Additive exPlanations (SHAP) approach was invoked. Results: The predictive acumen of the LightGBM model was superior, evidenced by a striking accuracy of 96% and an AUC of 99.3%. Parallel to biostatistical assessments, SHAP analysis leveraging XAI illuminated that augmented expression levels of specific genes, namely TSPYL5, ATP5E, CA9, NUP210, SLC37A1, ARIH1, PSMD7, UBQLN1, PRAME, and UBE2T (with statistical significance p ≤ 0.05), correlated with an escalated risk of BC metastasis. Conversely, diminished expression of CACTIN, TGFB3, SCUBE2, ARL4D, OR1F1, ALDH4A1, PHF1, and CROCC (p ≤ 0.05) was similarly associated with heightened metastatic susceptibility in BC. Conclusions: The insights garnered from this investigation may catalyze preventative strategies against BC progression and metastatic dissemination, thereby enhancing therapeutic efficacy through personalized intervention modalities for BC patients.

Regularization in machine learning models for MVT Pb-Zn prospectivity mapping: applying lasso and elastic-net algorithms

Regularization in machine learning models for MVT Pb-Zn prospectivity mapping: applying lasso and elastic-net algorithms

A Novel Machine-Learning Algorithm to Predict the Early Termination of Nutrition Support Team Follow-Up in Hospitalized Adults: A Retrospective Cohort Study.

For hospitalized adults, it is important to initiate the early reintroduction of oral food in accordance with nutrition support team guidelines. The aim of this study was to develop and validate a machine learning-based algorithm that predicts the early termination of medical nutritional therapy (the transition to oral feeding). This retrospective cohort study included consecutive adult patients admitted to the Hacettepe hospital (from 1 January 2018 to 31 December 2022). The outcome of the study was the prediction of an early transition to adequate oral feeding before discharge. The dataset was randomly (70/30) divided into training and test datasets. We used six ML algorithms with multiple features to construct prediction models. ML model performance was measured according to the accuracy, area under the receiver operating characteristic curve, and F1 score. We used the Boruta Method to determine the important features and interpret the selected features. A total of 2298 adult inpatients who were followed by a nutrition support team for medical nutritional therapy were included. Patients received parenteral nutrition (1471/2298, 64.01%), enteral nutrition (717/2298, 31.2%), or supplemental parenteral nutrition (110/2298, 4.79%). The median (interquartile range) Nutritional Risk Screening (NRS-2002) score was 5 (1). Six prediction algorithms were used, and the artificial neural network and elastic net models achieved the greatest area under the ROC in all outcomes (AUC = 0.770). Ranked by z-value, the 10 most important features in predicting an early transition to oral feeding in the artificial neural network and elastic net algorithms were parenteral nutrition, surgical wards, surgical outcomes, enteral nutrition, age, supplemental parenteral nutrition, digestive system diseases, gastrointestinal complications, NRS-2002, and impaired consciousness. We developed machine learning models for the prediction of an early transition to oral feeding before discharge. Overall, there was no discernible superiority among the models. Nevertheless, the artificial neural network and elastic net methods provided the highest AUC values. Since the machine learning model is interpretable, it can enable clinicians to better comprehend the features underlying the outcomes. Our study could support personalized treatment and nutritional follow-up strategies in clinical decision making for the prediction of an early transition to oral feeding in hospitalized adult patients.

Predicting lymph node metastasis in colorectal cancer patients: development and validation of a column chart model

Lymph node metastasis (LNM) is one of the crucial factors in determining the optimal treatment approach for colorectal cancer. The objective of this study was to establish and validate a column chart for predicting LNM in colon cancer patients. We extracted a total of 83,430 cases of colon cancer from the Surveillance, Epidemiology, and End Results (SEER) database, spanning the years 2010–2017. These cases were divided into a training group and a testing group in a 7:3 ratio. An additional 8545 patients from the years 2018–2019 were used for external validation. Univariate and multivariate logistic regression models were employed in the training set to identify predictive factors. Models were developed using logistic regression, LASSO regression, ridge regression, and elastic net regression algorithms. Model performance was quantified by calculating the area under the ROC curve (AUC) and its corresponding 95% confidence interval. The results demonstrated that tumor location, grade, age, tumor size, T stage, race, and CEA were independent predictors of LNM in CRC patients. The logistic regression model yielded an AUC of 0.708 (0.7038–0.7122), outperforming ridge regression and achieving similar AUC values as LASSO regression and elastic net regression. Based on the logistic regression algorithm, we constructed a column chart for predicting LNM in CRC patients. Further subgroup analysis based on gender, age, and grade indicated that the logistic prediction model exhibited good adaptability across all subgroups. Our column chart displayed excellent predictive capability and serves as a useful tool for clinicians in predicting LNM in colorectal cancer patients.

Screening the influence of features for metabolic syndrome in occupational population based on Lasso and Elastic Net algorithms

Abstract Funding Acknowledgements None. Objective Screening features associated with metabolic syndrome (MetS) is essential for early detection in the occupational population. In this study, we utilized two machine learning algorithms to screen MetS features and compared the performance of models constructed from these screened features. Method A total of 3,077 workers’examination records were considered from our hospital. However, 233 records were excluded due to incompleteness and errors, resulting in a final dataset of 2,844 workers’examination records used for the study. We collected and analyzed available data to extract usable indicators initially. Then, we applied the Least Absolute Shrinkage and Selection Operator (Lasso) algorithm and Elastic Net algorithm to identify features related to MetS. Subsequently, different models, namely K-Nearest Neighbors (KNN), Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM),were established using these two groups of features to predict the probability of MetS in the occupational population. The performance of these models was evaluated using the Area Under the Receiver Operating Characteristic Curve (AUC), Calibration Curve, and Decision Curve Analysis (DCA). Results It was indicated that features screened by the Elastic Net algorithm were more stable and demonstrated better predictive performance compared to LASSO, particularly when the data had high dimensionality and correlations. Furthermore, this study presents the first application of the Elastic Net algorithm in screening features related to MetS and establishing a risk prediction model for routine physical examinations of the occupational population. Conclusion Notably, Elastic Net demonstrated improved stability when dealing with multiple indicators exhibiting high dimensional correlations. This enhanced stability allowed for a more accurate prediction of MetS, providing a basis for utilizing common universal indicators in health screening for the general occupational population.Study the basic characteristics of the p(a) AUC performance of 9 features screen

Elastic Net – MLP – SMOTE (EMS)-Based Model for Enhancing Stroke Prediction

A stroke is a sudden disruption in the blood supply to the brain, affecting one or more blood vessels that nourish the brain. This results in a disturbance or deficiency in the brain’s oxygen supply, causing damage or impairment to brain cells. In some cases, determining the timing and severity of a stroke can be challenging. This study proposes an EMS (Elastic Net – MLP – SMOTE) model built on artificial intelligence, specifically utilizing two machine learning algorithms, Elastic Net and multilayer perceptron (MLP) by using Synthetic Minority Over-sampling Technique (SMOTE). The Elastic Net algorithm was employed for feature selection to identify crucial features, followed by prediction using the MLP algorithm. The Elastic Net algorithm was used due to its incorporation of both L2 and L1 regularization, providing good results in discerning influential features in model performance. The MLP algorithm was employed for its reliance on deep learning techniques, which yield promising results in such cases. This algorithm classified data from a comprehensive dataset containing essential features related to stroke. SMOTE is used to increase the performance of the model. Notably, no previous research study has integrated these three techniques together (Elastic Net – MLP – SMOTE). EMS achieved a prediction accuracy of 95% and MSE = 0.05. This model facilitates predicting the occurrence of stroke by relying on the patient’s historical data, mitigating the sudden onset of this serious disease.

Development of non-alcoholic steatohepatitis is associated with gut microbiota but not with oxysterol enzymes CH25H, EBI2, or CYP7B1 in mice

Liver steatosis is the most frequent liver disorder and its advanced stage, non-alcoholic steatohepatitis (NASH), will soon become the main reason for liver fibrosis and cirrhosis. The “multiple hits hypothesis” suggests that progression from simple steatosis to NASH is triggered by multiple factors including the gut microbiota composition. The Epstein Barr virus induced gene 2 (EBI2) is a receptor for the oxysterol 7a, 25-dihydroxycholesterol synthesized by the enzymes CH25H and CYP7B1. EBI2 and its ligand control activation of immune cells in secondary lymphoid organs and the gut. Here we show a concurrent study of the microbial dysregulation and perturbation of the EBI2 axis in a mice model of NASH.We used mice with wildtype, or littermates with CH25H−/−, EBI2−/−, or CYP7B1−/− genotypes fed with a high-fat diet (HFD) containing high amounts of fat, cholesterol, and fructose for 20 weeks to induce liver steatosis and NASH. Fecal and small intestinal microbiota samples were collected, and microbiota signatures were compared according to genotype and NASH disease state.We found pronounced differences in microbiota composition of mice with HFD developing NASH compared to mice did not developing NASH. In mice with NASH, we identified significantly increased 33 taxa mainly belonging to the Clostridiales order and/ or the family, and significantly decreased 17 taxa. Using an Elastic Net algorithm, we suggest a microbiota signature that predicts NASH in animals with a HFD from the microbiota composition with moderate accuracy (area under the receiver operator characteristics curve = 0.64). In contrast, no microbiota differences regarding the studied genotypes (wildtype vs knock-out CH25H−/−, EBI2−/−, or CYP7B1−/−) were observed.In conclusion, our data confirm previous studies identifying the intestinal microbiota composition as a relevant marker for NASH pathogenesis. Further, no link of the EBI2 – oxysterol axis to the intestinal microbiota was detectable in the current study.

Immunometabolic features of natural killer cells are associated with infection outcomes in critical illness.

Immunosuppression increases the risk of nosocomial infection in patients with chronic critical illness. This exploratory study aimed to determine the immunometabolic signature associated with nosocomial infection during chronic critical illness. We prospectively recruited patients who were admitted to the respiratory care center and who had received mechanical ventilator support for more than 10 days in the intensive care unit. The study subjects were followed for the occurrence of nosocomial infection until 6 weeks after admission, hospital discharge, or death. The cytokine levels in the plasma samples were measured. Single-cell immunometabolic regulome profiling by mass cytometry, which analyzed 16 metabolic regulators in 21 immune subsets, was performed to identify immunometabolic features associated with the risk of nosocomial infection. During the study period, 37 patients were enrolled, and 16 patients (43.2%) developed nosocomial infection. Unsupervised immunologic clustering using multidimensional scaling and logistic regression analyses revealed that expression of nuclear respiratory factor 1 (NRF1) and carnitine palmitoyltransferase 1a (CPT1a), key regulators of mitochondrial biogenesis and fatty acid transport, respectively, in natural killer (NK) cells was significantly associated with nosocomial infection. Downregulated NRF1 and upregulated CPT1a were found in all subsets of NK cells from patients who developed a nosocomial infection. The risk of nosocomial infection is significantly correlated with the predictive score developed by selecting NK cell-specific features using an elastic net algorithm. Findings were further examined in an independent cohort of COVID-19-infected patients, and the results confirm that COVID-19-related mortality is significantly associated with mitochondria biogenesis and fatty acid oxidation pathways in NK cells. In conclusion, this study uncovers that NK cell-specific immunometabolic features are significantly associated with the occurrence and fatal outcomes of infection in critically ill population, and provides mechanistic insights into NK cell-specific immunity against microbial invasion in critical illness.

Pediatric obstructive sleep apnea diagnosis: leveraging machine learning with linear discriminant analysis.

The objective of this study was to investigate the effectiveness of a machine learning algorithm in diagnosing OSA in children based on clinical features that can be obtained in nonnocturnal and nonmedical environments. This study was conducted at Beijing Children's Hospital from April 2018 to October 2019. The participants in this study were 2464 children aged 3-18 suspected of having OSA who underwent clinical data collection and polysomnography(PSG). Participants' data were randomly divided into a training set and a testing set at a ratio of 8:2. The elastic net algorithm was used for feature selection to simplify the model. Stratified 10-fold cross-validation was repeated five times to ensure the robustness of the results. Feature selection using Elastic Net resulted in 47 features for AHI ≥5 and 31 features for AHI ≥10 being retained. The machine learning model using these selected features achieved an average AUC of 0.73 for AHI ≥5 and 0.78 for AHI ≥10 when tested externally, outperforming models based on PSG questionnaire features. Linear Discriminant Analysis using the selected features identified OSA with a sensitivity of 44% and specificity of 90%, providing a feasible clinical alternative to PSG for stratifying OSA severity. This study shows that a machine learning model based on children's clinical features effectively identifies OSA in children. Establishing a machine learning screening model based on the clinical features of the target population may be a feasible clinical alternative to nocturnal OSA sleep diagnosis.

An ecological examination of early adolescent e-cigarette use: A machine learning approach to understanding a health epidemic.

E-cigarette use among adolescents is a national health epidemic spreading faster than researchers can amass evidence for risk and protective factors and long-term consequences associated with use. New technologies, such as machine learning, may assist prevention programs in identifying at risk youth and potential targets for intervention before adolescents enter developmental periods where e-cigarette use escalates. The present study utilized machine learning algorithms to explore a wide array of individual and socioecological variables in relation to patterns of lifetime e-cigarette use during early adolescence (i.e., exclusive, or with tobacco cigarettes). Extant data was used from 14,346 middle school students (Mage = 12.5, SD = 1.1; 6th and 8th grades) who participated in the Utah Prevention Needs Assessment. Students self-reported their substance use behaviors and related risk and protective factors. Machine learning algorithms examined 112 individual and socioecological factors as potential classifiers of lifetime e-cigarette use outcomes. The elastic net algorithm achieved outstanding classification for lifetime exclusive (AUC = .926) and dual use (AUC = .944) on a validation test set. Six high value classifiers were identified that varied in importance by outcome: Lifetime alcohol or marijuana use, perception of e-cigarette availability and risk, school suspension(s), and perceived risk of smoking marijuana regularly. Specific classifiers were important for lifetime exclusive (parent's attitudes regarding student vaping, best friend[s] tried alcohol or marijuana) and dual use (best friend[s] smoked cigarettes, lifetime inhalant use). Our findings provide specific targets for the adaptation of existing substance use prevention programs to address early adolescent e-cigarette use.

Linear regression analysis of the correlation between students’ physical education performance and academic achievement in the context of smart physical education in colleges and universities

Abstract In this paper, the principles, algorithms and different linear regression models are sorted out and finalized to determine the multiple linear regression model suitable for this study. The different types of regression are synthesized through the elastic net algorithm. Based on the multiple linear regression model, students’ performance in language, mathematics and English was used as the dependent variable Y on behalf of academic performance, and five sports such as physical education and hygiene were used as the independent variable X, to carry out an empirical study on 3,800 students. From this, it was concluded that the contribution rates affecting language achievement were sports attitude, environment, and hygiene in the order of coefficients of 0.548, 0.312, and −0.266. In contrast, exercise habit [B=−0.032, t=−1.574, P=0.116] and sports knowledge [B=0.027, t=1.561, P=0.119] did not pass the test of significance. The contribution of influencing math achievement was in the order of sports environment and attitude with coefficients of 0.402 and 0.327, which were positively correlated with math achievement Y2. The contribution rate affecting English achievement is in the order of sports hygiene, sports attitude and exercise habit, and their coefficients are 0.398, 0.295 and 0.124, all of which are positively correlated with English achievement Y3.

Feature selection of ground motion intensity measures for data‐driven surrogate modeling of structures

AbstractIn the probabilistic seismic performance assessment of structures, intensity measures (IMs) represent seismic characteristics and variations. Traditional fragility analysis method based on the assumption of linear regression requires selecting an optimal IM as input variable. By introducing machine learning (ML) techniques, nonparametric fragility analysis theoretically allows for considering all potential IMs as inputs. Nevertheless, to reduce input dimensionality and improve training efficiency, the feature selection of IMs remains imperative. This paper proposes a method to select optimal ground motion IMs for data‐driven surrogate modeling of structures. Specifically, the elastic net algorithm is employed to select the optimal multiple IMs based on the coefficient of determination and regression coefficient, differing from the efficiency and practicality emphasized in the traditional method. Using the optimal multiple IMs as input variables, several ML techniques are employed to construct surrogate models for seismic damage assessment of structures, thereby developing fragility functions, that is, the conditional probability of exceeding a damaged state given seismic intensity. A 3‐span, 6‐storey, reinforced concrete frame is utilized to illustrate the proposed methodology. The predictive performance of all ML models with the optimal multiple IMs outperforms that of the models with the commonly used IM (e.g., peak ground acceleration, PGA) as sole input and all candidate IMs as inputs. Additionally, the surrogate models with the optimal multiple IMs enable a more comprehensive seismic fragility modeling of structures under two or more IMs simultaneously, such as the fragility surface under spectral acceleration at 1.0s (Sa‐1.0s) and velocity spectrum intensity (VSI).

Quality prediction using functional linear regression with in-situ image and functional sensor data

This article studies a general regression model for a scalar quality response with mixed types of process predictors including process images, functional sensing signals, and scalar process setup attributes. To represent a set of time-dependent process images, a third-order tensor is employed for preserving not only the spatial correlation of pixels within one image but also the temporal dependency among a sequence of images. Although there exist some papers dealing with either tensorial or functional regression, there is little research to thoroughly study a regression model consisting of both tensorial and functional predictors. For simplicity, the presented regression model is called functional linear regression with tensorial and functional predictor (FLR-TFP). The advantage of the presented FLR-TFP model, which is compared to the classical stack-up strategy, is that FLR-TFP can handle both tensorial and functional predictors without destroying the data correlation structure. To estimate an FLR-TFP model, this article presents a new alternating Elastic Net (AEN) estimation algorithm, in which the problem is reformed as three sub-problems by iteratively estimating each group of tensorial, functional, and scalar parameters. To execute the proposed AEN algorithm, a systematic approach is developed to effectively determine the initial running sequence among three sub-problems. The performance of the FLR-TFP model is evaluated using simulations and a real-world case study of friction stir blind riveting process.

Ultrasound Radiomics Features to Identify Patients With Triple-Negative Breast Cancer: A Retrospective, Single-Center Study.

Patients with triple-negative breast cancer (TNBC) exhibit a fast tumor growth rate and poor survival outcomes. In this study, we aimed to develop and compare intelligent algorithms using ultrasound radiomics features in addition to clinical variables to identify patients with TNBC prior to histopathologic diagnosis. We used single-center, retrospective data of patients who underwent ultrasound before histopathologic verification and subsequent neoadjuvant systemic treatment (NAST). We developed a logistic regression with an elastic net penalty algorithm using pretreatment ultrasound radiomics features in addition to patient and tumor variables to identify patients with TNBC. Findings were compared to the histopathologic evaluation of the biopsy specimen. The main outcome measure was the area under the curve (AUC). We included 1161 patients, 813 in the development set and 348 in the validation set. Median age was 50.1 years and 24.4% (283 of 1161) had TNBC. The integrative model using radiomics and clinical information showed significantly better performance in identifying TNBC compared to the radiomics model (AUC: 0.71, 95% confidence interval [CI]: 0.65-0.76 versus 0.64, 95% CI: 0.57-0.71, P = .004). The five most important variables were cN status, shape surface volume ratio (SA:V), gray level co-occurrence matrix (GLCM) correlation, gray level dependence matrix (GLDM) dependence nonuniformity normalized, and age. Patients with TNBC were more often categorized as BI-RADS 4 than BI-RADS 5 compared to non-TNBC patients (P = .002). A machine learning algorithm showed promising potential to identify patients with TNBC using ultrasound radiomics features and clinical information prior to histopathologic evaluation.

Inversion analysis of soil nitrogen content using hyperspectral images with different preprocessing methods

Unmanned aerial vehicle (UAV) hyperspectral data can provide accurate and detailed spectral information on the surface of features, leading to a better understanding of the physiological characteristics and optical properties of objects. Compared to satellite hyperspectral, UAV hyperspectral has a greater image spatial resolution, but it also collects more impurity information along with more image detail information. The nitrogen (N) content in shallow soils is of great significance for crop growth, and most of its remote sensing inversions are currently based on satellite images, whereas relatively few studies have used hyperspectral UAV images in the near-infrared band for inversions. Based on this, we propose a high-accuracy inversion model based on UAV hyperspectral imagery using an elastic net (EN) dimensionality reduction algorithm combined with a decision tree (DT) model. In this study, a hyperspectral imager carried by a drone was used to acquire the surface soil spectral data of winter wheat in the study area after sowing and fertilizing, and the measured N content of the sampled soil was determined by chemical analysis methods. We used various pre-processing methods to denoise and reduce the dimensionality of the original hyperspectral images and utilized a DT regression model to construct an inversion model of N content with different preprocessing results. Then we compared the accuracy of the models and used the optimal model to obtain the spatial distribution map of soil N content in the study area. The results show that (1) the dimensionality reduction of hyperspectral data can effectively remove redundant information and prevent data overfitting. Among them, the successive projections algorithm and correlation analysis method are more suitable for analyzing pre-processed spectral data, whereas the Lasso and EN algorithms are more suitable for processing original spectral data. (2) For the original spectral images, the EN dimensionality reduction algorithm (R2 of the EN-Unt-DT inversion model is 0.930, RMSE is 0.045) performed better than the other three algorithms. For the pre-processed spectral images, the successive projections algorithm (R2 of the SPA-Pre-DT inversion model is 0.906, RMSE is 0.055) performed better than the other three algorithms. The constructed EN-Unt-DT inversion model had the highest fitting accuracy. The research results provide a corresponding technical reference for the inversion of soil N content using UAV NIR hyperspectral data.

Machine learning predictions for optimal cement content in sustainable concrete constructions

The designated concrete compressive strength at 28 days plays an important role in determining the quantity of cement (water to cement ratio) needed in concrete mix designs. Whilst a 28-day target is common, some structural elements receive deferred loads during construction, allowing a reduced cement content and the possibility to optimize the concrete mix to target full strength at 90 days. Machine learning techniques are used in this study to optimize the concrete mix design of structural elements that commonly receive deferred loads, e.g., foundation and pavements, targeting a 90-day full strength. Specifically, the compressive strength of concrete samples cured for 28 and 90 days are considered to estimate the cement content per m3 of concrete using Artificial Neural Network and Regression algorithms. The proposed machine learning and deep learning methods are proved to be capable of predicting the cement content with 94% and 90% accuracy, respectively. The Elastic Net algorithm shows the best performance in cement content optimization to a target 90-days compressive strength. This algorithm is hence employed to assess the carbon reduction benefits in a real case study: a typical mid-sized reinforced concrete structure is considered as a baseline to quantify the environmental benefit of optimizing the cement content for a 90-days target compressive strength. Results of the case study show that the proposed method may result in a reduction of approximately 10% in cement usage, consequently leading to a parallel reduction of about 10% in carbon emissions.

Hyperspectral estimation of chlorophyll content in jujube leaves: integration of derivative processing techniques and dimensionality reduction algorithms.

The leaf chlorophyll content (LCC) of vegetation is closely related to photosynthetic efficiency and biological activity. Jujube (Ziziphus jujuba Mill.) is a traditional economic forest tree species. Non-destructive monitoring of LCC of jujube is of great significance for guiding agroforestry production and promoting ecological environment protection in arid and semi-arid lands. Hyperspectral data is an important data source for LCC detection. However, hyperspectral data consists of a multitude of bands and contains extensive information. As a result, certain bands may exhibit high correlation, leading to redundant spectral information. This redundancy can distort LCC prediction results and reduce accuracy. Therefore, it is crucial to select appropriate preprocessing methods and employ effective data mining techniques when analyzing hyperspectral data. This study aims to evaluate the performance of hyperspectral data for estimating LCC of jujube trees by integrating different derivative processing techniques with different dimensionality reduction algorithms. Hyperspectral reflectance data were obtained through simulations using an invertible forest reflectance model (INFORM) and measurements from jujube tree canopies. The least absolute shrinkage and selection operator (LASSO) and elastic net (EN) were employed to identify the important bands in the original spectra (OS), first derivative spectra (FD), and second derivative spectra (SD). Support vector regression (SVR) was used to establish the estimation model. The results show that compared with full-spectrum modeling, LASSO and EN algorithms are effective methods for preventing overfitting in LCC machine learning estimation models for different spectral derivatives. The LASSO/EN-based estimation models constructed using FD and SD exhibited superior R2 compared to the OS. The important band of SD can best reveal the relevant information of jujube LCC, and SD-EN-SVR is the most ideal model in both the simulated dataset (R2=0.99, RMSE=0.61) and measured dataset (R2=0.89, RMSE=0.91). Our results provided a reference for rapid and non-destructive estimation of the LCC of agroforestry vegetation using canopy hyperspectral data.

Compressed sensing photoacoustic imaging based on the gradient projection Newton pursuit algorithm

Photoacoustic imaging (PAI) is a unique non-invasive biomedical imaging technique that illuminates biological tissue with short-pulsed laser light. This process generates acoustic waves, which in turn enable high-resolution and high-contrast imaging of deep tissue. However, the complexity of PAI imaging data presents challenges in achieving rapid and optimal reconstruction results due to the time and resource demands of traditional Nyquist sampling. On the contrary, compressive sensing (CS) overcomes the limitations of Nyquist sampling by recovering the original signal with a lower amount of sampled data, resulting in significant cost savings in signal transmission and processing. Additionally, CS-based hard-thresholding iterative algorithms possess various advantages in sparse optimization, including sparsity control and fast computation. Moreover, the assumptions of the Gradient Projection Newton Pursuit (GPNP) for CS problems are relatively weaker compared to many state-of-the-art algorithms. Therefore, we investigated the performance of the GPNP algorithm in PAI. We compared our algorithm with improved iterative hard thresholding (IIHT), conjugate gradient iterative hard thresholding (CGIHT), compressive sampling matching pursuit (CoSaMP), SPGL1, SALSA and elastic net algorithms using phantom, Vasculature, and SGERF simulation images. The simulation results demonstrate that the GPNP algorithm achieves excellent image reconstruction performance when evaluating both the quality of reconstruction and the reconstruction time. Taking the simulation results of Vasculature with a noise level of 40 dB and 40 channels as an example, the PNSR index of GPNP has improved by 4.09, 11.03, 12.89, 13.14, 13.15, and 11.75 compared to IIHT, CGIHT, elastic net algorithms, SPGL1, SALSA and CoSaMP, respectively.