Linear Support Vector Regression Research Articles

Tau Protein Accumulation Trajectory-Based Brain Age Prediction in the Alzheimer’s Disease Continuum

Clinical cognitive advancement within the Alzheimer’s disease (AD) continuum is intimately connected with sustained accumulation of tau protein pathology. The biological brain age and its gap show great potential for pathological risk and disease severity. In the present study, we applied multivariable linear support vector regression to train a normative brain age prediction model using tau brain images. We further assessed the predicted biological brain age and its gap for patients within the AD continuum. In the AD continuum, evaluated pathologic tau binding was found in the inferior temporal, parietal-temporal junction, precuneus/posterior cingulate, dorsal frontal, occipital, and inferior-medial temporal cortices. The biological brain age gaps of patients within the AD continuum were notably higher than those of the normal controls (p < 0.0001). Significant positive correlations were observed between the brain age gap and global tau protein accumulation levels for mild cognitive impairment (r = 0.726, p < 0.001), AD (r = 0.845, p < 0.001), and AD continuum (r = 0.797, p < 0.001). The pathologic tau-based age gap was significantly linked to neuropsychological scores. The proposed pathologic tau-based biological brain age model could track the tau protein accumulation trajectory of cognitive impairment and further provide a comprehensive quantification index for the tau accumulation risk.

Hybrid machine learning for stock price prediction in the Moroccan banking sector

Analyzing historical stock market data using machine-learning techniques is crucial for data scientists and researchers to optimize stock price prediction models. This study uses machine learning regression algorithms and feature selection methods to optimize a simulated stock price prediction model using real historical data from Bank of Africa, a Moroccan bank. The approach compares multiple supervised regression algorithms, such as linear regression, extreme gradient boosting, ordinary least squared, random forest regressor, a linear least-squares L2-regularized, epsilon-support vector regression, and linear support vector regression. Each of these algorithms is associated with different feature selection algorithms to improve the performance of the prediction model. The analysis results revealed that hybridizing algorithms between the highest score percentiles, univariate linear regression, and linear support vector regression perform better according to the root mean squared error and R2-Score measures. This approach overcomes the problems associated with high-dimensional data by reducing the number of features and improving prediction accuracy.

Construction of a Cutting-Tool Wear Prediction Model through Ensemble Learning

This study begins by conducting side milling experiments on SKD11 using tungsten carbide TiAlN-coated end mills to compare the surface roughness performance between two combinations of milling process parameters (feed rate and radial depth of cut), along with three ultrasonic-assisted methods (rotary, dual-axis, and rotary combined with dual-axis). The results suggest that the rotary (z-axis oscillation) ultrasonic-assisted method may provide better performance. Subsequently, this superior ultrasonic-assisted method was applied both with and without laser locally preheating assistance, respectively. Using a Taguchi orthogonal array, milling process parameters (spindle speed, feed rate, and radial depth of cut) were planned for experiments with the same cutting tool and the workpiece just mentioned above. The surface roughness serves as the objective function while being constrained by cutting-tool life. The characteristics of the smaller-the-better in the Taguchi method were applied to determine the optimal combination of process parameters. Based on the optimal milling process parameters obtained and the superior hybrid-assisted method adopted, milling experiments were repeatedly performed to collect the data on cutting force and cutting-tool wear. Feature engineering was performed on the cutting force signals, and different domain characteristics from both the time and frequency domains were extracted. Hereafter, feature selection by random forest and data standardization were further applied to feature extractions, and the data processing was thus completed. For the processed data, a cutting-tool wear prediction model was constructed by ensemble learning. This method leverages various machine learning regression models, including decision tree, random forest, extremely randomized tree, light gradient boosting machine, extreme gradient boosting, AdaBoost, stochastic gradient descent, support vector regression, linear support vector regression, and multilayer perceptron. After hyper-parameter tuning, the ensemble voting regression prediction was performed based on these ten mentioned models. The experimental results demonstrate that the ensemble voting regression model surpasses the performance of each individual machine learning regression model. In addition, this regression model achieves a coefficient of determination (R2) of 0.94576, a root mean square error (RMSE) of 0.24348, a mean squared error (MSE) of 0.05928, and a mean absolute error (MAE) of 0.18182. Therefore, the ensemble learning approach has been proven to be a feasible and effective method for monitoring cutting-tool wear.

Study on the Impact of Urban Morphologies on Urban Canopy Heat Islands Based on Relocated Meteorological Stations

This study addresses a crucial gap in understanding the impact of urban morphologies on the canopy urban heat islands (CUHI) effect. The selection of reference stations lacks a unified standard, and their surface air temperature (SAT) sequences are also inevitably influenced by urbanization. However, synchronous observational data from relocated meteorological stations could provide high-quality sample data for studying CUHI. Utilizing remote sensing techniques, the findings of this paper revealed that the observation environment of stations after relocation exhibited remarkable representativeness, with their observation sequences accurately reflecting the local climatic background. The differences in synchronized observation sequences could characterize the CUHI intensity (CUHII). Among the various factors, land use parameters and landscape parameters played particularly significant roles. Furthermore, the fitting performance of the random forest (RF) model for both training and testing data was significantly superior to that of the linear model and support vector regression (SVR) model. Additionally, the influence of local circulation on CUHI could not be overlooked. The mechanisms by which urban morphologies affect CUHII under different circulation backgrounds deserve further investigation.

Analysis of Damage Assessment Tweets During Disaster using Sentiment Analysis

This seems to be an abstract or summary of a paper on monitoring Twitter for damage assessments after a disaster. Using simple linear regression and Support Vector Regression methods for weighting and the random forest methodology for classification, the research provides a novel approach that makes use of low-level lexical characteristics, top-most frequency word features, and syntactic elements relevant to damage assessment. The accuracy of the suggested method for identifying damage assessment tweets is 94.62%, as measured across 14 typical disaster datasets for binary and multi-class categorization. Significant advancements were observed when comparing the proposed method to the state-of-the-art for both in-domain and cross-domain scenarios. The suggested method does not require labelled tweets or tweets of a specific disaster kind in order to be trained and implemented; instead, it can be trained on historical disaster datasets.

Stock Market Price Prediction and Forecasting Using Stacked LSTM

Stock price movement is non-linear and complex. Several research works have been carried out to predict stock prices. Traditional approaches such as Linear Regression and Support Vector Regression were used but accuracy was not adequate. Researchers have tried to improve stock price prediction using ARIMA. Due to very high variations in stock prices, deep learning techniques are applied due to its proven accuracy in various analytics fields. Artificial Neural Network was deployed to predict stock prices but as stock prices are time-series based, recurrent neural network was applied to further improve prediction accuracy. Therefore, data scientists and analysts found that Deep Learning outperformed Machine Learning which is also proofed by all the collected research papers, and it is the most suitable methodologies to apply to the stock market forecasting domain. This paper explores different stacked LSTM Models for non-stationary financial time series in stock price prediction. This study is to predict stock market prices to make more acquaint and precise investment decisions. The experimental result will show that, this method can get quite accurate result, particularly effective in stock prediction. The proposed LSTM model will be designed to overcome gradient explosion, gradient vanishing, and save long-term memory. Firstly, The Model will have a comparative analysis between different LSTM models and integrating the model based on the result obtained from the analysis. The results will suggest that the developed stacked LSTM produces better predictive power and generalization. Key Words: stock market prediction, stacked LSTM, Deep Learning, Data pre-processing techniques, Data normalization, Neural Networks, Data Visualization, Training and Testing Set, Time series analysis, Predictive models, Future Forecasting.

Body weight prediction in crossbred pigs from digital images using computer vision

The development of technologies made it possible to capture digital images by sensors in order to obtain morphometric measurements that can be used in the development of mathematical models for the prediction of body weight (BW) in animals. The objective was to develop mathematical models to predict body weight in crossbred pigs from morphometric measurements obtained with two-dimensional digital images. Data collection was carried out in the swine sector of IF Goiano, Urutai campus, in 52 crossbred pigs housed in the finishing phase. The animals were randomly weighed and filmed by the Microsoft Kinect® v1 sensor camera in the dorsal view. Subsequently, they were conducted for the measurement of manual morphometric measurements, without restraint, being dorsal length, chest width and flank width. The morphometric measurements predicted from the dorsal images were dorsal length, chest width, flank width, dorsal area and perimeter. Through Mask R-CNN algorithm trains the network by input images, was compute the area of the evaluated object in pixels, and thus, can correlate with measures of interest. The Mask R-CNN algorithm were performed with the Collaboratory Google using Phyton 3.0. Mathematical models were developed using multiple linear regression (MLR) and support vector regression (SVR) methodologies for body weight prediction. All Pearson's correlations between real body weight and real and predicted morphometric measurements by digital images were moderate to high magnitude positive and statistically significant (P<0.05). The difference between the real and predicted BW by the SVR was -1.74 kg (R² = 91%) and -2.39 kg (R² = 88%), respectively. The MLR model with real morphometrics measurements explained 60% of BW variance and estimated a BW 18.76 kg below from the real BW mean. The MLR model with predicted measurements explained 53% of BW variance and estimated a BW 22.51 kg below from the real BW mean. The mathematical model developed from SVR has the potential to estimate the body weight of crossbred pigs using morphometric measurements predicted by digital images such as dorsal length, width, dorsal area and perimeter.

Machine learning can predict anterior elevation after reverse total shoulder arthroplasty: A new tool for daily outpatient clinic?

The aim of the present study was to individuate and compare specific machine learning algorithms that could predict postoperative anterior elevation score after reverse shoulder arthroplasty surgery at different time points. Data from 105 patients who underwent reverse shoulder arthroplasty at the same institute have been collected with the purpose of generating algorithms which could predict the target. Twenty-eight features were extracted and applied to two different machine learning techniques: Linear regression and support vector regression (SVR). These two techniques were also compared in order to define to most faithfully predictive. Using the extracted features, the SVR algorithm resulted in a mean absolute error (MAE) of 11.6° and a classification accuracy (PCC) of 0.88 on the test-set. Linear regression, instead, resulted in a MAE of 13.0° and a PCC of 0.85 on the test-set. Our machine learning study demonstrates that machine learning could provide high predictive algorithms for anterior elevation after reverse shoulder arthroplasty. The differential analysis between the utilized techniques showed higher accuracy in prediction for the support vector regression. Level of Evidence III: Retrospective cohort comparison; Computer Modeling.

Harsh, unpredictable childhood environments are associated with inferior frontal gyrus connectivity and binge eating tendencies in late adolescents

Harsh, unpredictable childhood environments (HUCE) are associated with obesity older in life, but knowledge of how HUCE affect binge eating tendencies is lacking. Five hundred and one late adolescents aged 16–22 were recruited to finish resting state functional magnetic resonance imaging scan, behavioral measures including retrospective recall of childhood environmental harshness and unpredictability, binge eating tendencies and demographics. Three hundred and seventy-six of participants further completed the computerized visual probe task designed to evaluate attentional engagement towards high and low calorie food. As right inferior frontal gyrus (IFG) was the key nodes that related to both early life adversity and binge eating tendencies, it was treated as the interest region in the dynamic functional connectivity analyses. Results found that HUCE are associated with significant but modest decreases in connectivity of right inferior frontal gyrus (IFG)– bilateral medial frontal gyrus, right IFG – bilateral inferior parietal lobule (IPL), and right IFG – left superior frontal gyrus connectivity, as well as attentional engagement to high-calorie food and binge eating tendencies. A machine-learning method named linear support vector regression (SVR) and leave one out cross-validation (LOOCV) procedure used to examine the robustness of the brain-behavior relationship further confirm the findings. Mediation analyses suggested that right IFG – left IPL connectivity mediates the association of HUCE and binge eating tendencies. Findings suggest right IFG – left IPL connectivity may serve as a crucial neurobiological underpinning of HUCE to regulate binge eating behaviors. As such, these results contribute to a novel perspective and hypotheses in elucidating developmental neuro-mechanisms related to binge eating.

Comparative analysis of machine learning models in predicting housing prices: a case study of Prishtina's real estate market

Purpose The purpose of this study is to carry out a comparative analysis of four machine learning models such as linear regression, decision trees, k-nearest neighbors and support vector regression in predicting housing prices in Prishtina. Design/methodology/approach Using Python, the models were assessed on a data set of 1,512 property transactions with mean squared error, coefficient of determination, mean absolute error and root mean squared error as metrics. The study also conducts variable importance test. Findings Upon preprocessing and standardization of the data, the models were trained and tested, with the decision tree model producing the best performance. The variable importance test found the distance from central business district and distance to the road leading to central business district as the most relevant drivers of housing prices across all models, with the exception of support vector machine model, which showed minimal importance for all variables. Originality/value To the best of the author’s knowledge, the originality of this research rests in its methodological approach and emphasis on Prishtina's real estate market, which has never been studied in this context, and its findings may be generalizable to comparable transitional economies with booming real estate sector like Kosovo.

Comparative Study of Iconnet Jabodetabek and Banten Using Linear Regression and Support Vector Regression

PT PLN Indonesia Comnets Plus has little information regarding future customer growth, making it difficult to take steps to meet customer needs. This research aims to predict customer growth in the future based on quantitative data from the previous year, where the output provided produces data in the form of numbers that are analyzed using statistical methods. The hope is to provide information to maximize customer growth with the minimum area or bandwidth used by the company. This research uses linear regression and support vector regression (SVR) algorithms using a company secondary dataset of 252 data points with 5 attributes. Data was collected during the last one-year period, from January to December 2021. The results of the research show that predictions using both algorithms have increased, customer growth when viewed from the number of customers, bandwidth, and regional data has increased significantly. This can be seen from the value of the number of customers, which continues to increase, while the highest number of customers falls in December, the most requested bandwidth is 20 mbps, and the largest customer area is in the Depok area. The results of the research show that the SVR algorithm is superior in terms of mean absolute percentage error (MAPE): 0.02% MAPE, 0.10 MAE, and 0.99 RMSE, while for linear regression, the MAPE values were 36.28%, MAE 201, and RMSE 0.80.

ENHANCING ECOSYSTEM BIODIVERSITY THROUGH AIR POLLUTION CONCENTRATIONS PREDICTION USING SUPPORT VECTOR REGRESSION APPROACHES

Air is the most crucial element for the survival of life on Earth. The air we breathe has a profound effect on our ecosystem biodiversity. Consequently, it is always prudent to monitor the air quality in our environment. There are few ways can be done in predicting the air pollution index (API) like data mining. Therefore, this study aimed to evaluate three types of support vector regression (linear, SVR, libSVR) in predicting the air pollutant concentration and identify the best model. This study also would like to calculate the API by using the proposed model. The secondary daily data is used in this study from year 2002 to 2020 from the Department of Environment (DoE) Malaysia which located at Petaling Jaya monitoring station. There are six major pollutants that have been focusing in this work like PM10, PM2.5, SO2, NO2, CO, and O3. The root means square error (RMSE), mean absolute error (MAE) and relative error (RE) were used to evaluate the performance of the regression models. Experimental results showed that the best model is linear SVR with average of RMSE = 5.548, MAE = 3.490, and RE = 27.98% because had the lowest total rank value of RMSE, MAE, and RE for five air pollutants (PM10, PM2.5, SO2, CO, O3) in this study. Unlikely for NO2, the best model is support vector regression (SVR) with RMSE = 0.007, MAE = 0.006, and RE = 20.75% in predicting the air pollutant concentration. This work also illustrates that combining data mining with air pollutants prediction is an efficient and convenient way to solve some related environment problems. The best model has the potential to be applied as an early warning system to inform local authorities about the air quality and can reliably predict the daily air pollution events over three consecutive days. Besides, good air quality plays a significant role in supporting biodiversity and maintaning healthy ecosystems.

Industrial-scale anaerobic Co-digestion (ACoD) of palm oil mill effluent (POME) and decanter cake (DC) for maximizing methane yield: An integrated machine learning and simulation-based economic analysis approach

This study employs machine learning (ML) algorithms, including multiple linear regression (MLR), decision tree (DT) and support vector regression (SVR) to predict the methane yield from the anaerobic co-digestion (ACoD) of palm oil mill effluent (POME) and decanter cake (DC) in an industry-scale anaerobic covered lagoon. Results showed that the DT model outperformed the other models with a high R2 value of 0.9763 and the lowest MAE, MSE, and RMSE values. It exhibited over 95 % similarity to the actual results, validating its effectiveness in capturing real-world scenarios. Optimisation was conducted using response surface methodology (RSM) to achieve maximum biogas production (14,245 m3/day) and methane yield (0.285 Nm3 CH4/kg CODremoved), where the optimal range of pH, organic loading rate (OLR) and dilution ratio of DC were found to be 6.83–6.94, 0.82–0.83 kg COD/m3. day and 0.09–0.11 respectively. The ACoD process was simulated, and an economic analysis was performed using SuperPro Designer v10.6. ACoD of POME and DC was more economically viable than mono-digestion of POME, with a 43.16 % improvement in return on investment (ROI), considering the trade-off between the additional cost of pre-treating DC and the additional revenue from improved biogas production using ACoD.

Forecasting cryptocurrencies volatility using statistical and machine learning methods: A comparative study

Forecasting cryptocurrency volatility can help investors make better-informed investment decisions in order to minimize risks and maximize potential profits. Accurate forecasting of cryptocurrency price fluctuations is crucial for effective portfolio management and contributes to the stability of the financial system by identifying potential threats and developing risk management strategies. The objective of this paper is to provide a comprehensive study of statistical and machine learning methods for predicting daily and weekly volatility of the following four cryptocurrencies: Bitcoin, Ethereum, Litecoin, and Monero. Several models and forecasting methods are compared in terms of their forecasting accuracy, i.e., HAR (heterogeneous autoregressive), ARFIMA (autoregressive fractionally integrated moving average), GARCH (generalized autoregressive conditional heteroscedasticity), LASSO (least absolute shrinkage and selection operator), RR (ridge regression), SVR (support vector regression), MLP (multilayer perceptron), FNM (fuzzy neighbourhood model), RF (random forest), and LSTM (long short-term memory). The realized variance calculated from intraday returns is used as the input variable for the models. In order to assess the predictive power of the models considered, the model confidence set (MCS) procedure is applied. Our experimental results demonstrate that there is no single best method for forecasting volatility of each cryptocurrency, and different models may perform better depending on the specific cryptocurrency, choice of the error metric and forecast horizon. For daily forecasts, the method that is always found in a set of best models is linear SVR, while for weekly forecasts, there are two such methods, namely FNM and RR. Furthermore, we show that simple linear models such as HAR and ridge regression, perform not worse than more complex models like LSTM and RF. The research provides a useful reference point for the development of more sophisticated models.

Accelerated brain ageing in participants with higher cerebrovascular lesion load across aging, cognitive impairment, and mixed presentation

AbstractBackgroundWe aimed to investigate the association between cortical brain age and white matter hyperintensities (WMH) in diverse forms of clinically‐defined vascular conditions. Our hypothesis was that a higher WMH burden would be associated with higher cortical brain age in all clinical subtypes.MethodWe used standardized MRI data obtained from participants in the COMPASS‐ND cohort of the CCNA. We used a standard linear support vector regression algorithm to estimate brain age, matching chronological age to cortical anatomical measurements obtained with the FreeSurfer toolbox on T1‐weighted MRI, sex, and intracranial volume. We calculated brain‐PAD (i.e., predicted brain age minus real age) and applied bias adjustment to remove age‐dependency in the estimates. A validated automated technique utilizing T2‐weighted and fluid attenuated inversion recovery MRIs was used to compute WMH loads.ResultParticipants included 107 CIE, 240 mild cognitive impairment (MCI), 115 vascular‐MCI (V‐MCI), 81 probable Alzheimer’s disease (AD), and 50 V‐AD. There was a significant difference in brain‐PAD [ F (4,599) = 56, P &lt; 0.001, ANCOVA test] among groups, whilst adjusting for sex and chronological age. All four categories of patients exhibited a significantly higher mean brain‐PAD than CIE (P &lt; 0.001), with the AD cohort having the highest brain‐PAD. There was a significant difference in WMH loads [ F (4,586) = 48, P &lt; 0.001, ANCOVA test] between groups, whilst adjusting for sex and age. All cohorts showed a positive correlation between brain‐PAD and WMH, indicating accelerated ageing in people with higher WMHs. We observed moderate and significant correlations between brain‐PAD and WMH loads for V‐MCI (r = 0.34, P &lt; 0.001) and V‐AD (r = 0.36, P = 0.001) but weaker, while significant correlations in CIE (r = 0.20, P = 0.035) and AD cohorts (r = 0.24, P = 0.025).ConclusionWe observed a positive and significant link between brain‐PAD and WMH in all categories. This finding indicates on the importance of treatment and prevention strategies for vascular risk factors, which might be able to slow down the progression of cerebrovascular lesions and delay the effect on cortical thickness.

AI-based Optimization of Tensile Strength of the Cement Concrete Incorporating Recycled Mixed Plastic Fine used in Road Construction

Abstract: One of the main problems in materials science and engineering is predicting the tensile strength of materials. In this study, we investigate how to model and forecast tensile strength (Tensile Strength in Mpa) based on different material attributes using Support Vector Regression (SVR) using Linear and Polynomial Kernels. The dataset includes the following details: plastic type, fine aggregate ratio, water/cement ratio, cement content, and associated tensile strength values. This work has two main goals: (1) to assess the predictive power of SVR models with various kernel functions and (2) to examine the significance of unique material attributes for prediction. To simulate the link between the input features and tensile strength, we used SVR in conjunction with a Linear Kernel. The final model included insightful information on how each feature affected the forecast. Our results show that the Polynomial Kernel SVR model may better reflect the complex interactions among the material attributes than the Linear Kernel SVR model, despite being more interpretable. Better prediction performance was offered by the Polynomial Kernel SVR, which also revealed the non-linear dependencies in the data.

Oil price movements predictions in Kingdom of Saudi Arabia using financial and macro-economic variables

By combining financial and macroeconomic factors with machine learning techniques, this research paper proposes a novel method for forecasting oil price movements in the Kingdom of Saudi Arabia (KSA). Traditional methods generally struggle to capture the complex dynamics and nonlinear linkages in the oil market, which makes accurate oil price forecasting vital for decision-making in numerous sectors. In this paper, we offer a machine learning framework that leverages financial elements like stock market indices, currency rates, and interest rates, as well as macroeconomic data like GDP growth, inflation rates, and energy consumption, as predictors of oil price movements. These factors were chosen because of their significance and importance to the ways in which the oil market in KSA functions. We use several different machine learning techniques to construct the prediction models, some of which are regression-based (such as linear regression or support vector regression) while others are ensemble models (such as random forests or gradient boosting). The models are tested and refined using historical data spanning a sizable period of time and covering a wide range of market circumstances and pricing movements. Evaluation of the prediction models is carried out using conventional metrics like mean-squared error, mean absolute error, and R-squared [Formula: see text], and their robustness is evaluated using sensitivity analysis and cross-validation methods. Incorporating financial and macroeconomic variables vastly enhances the accuracy of oil price predictions compared to models based purely on historical price data, as shown by the preliminary findings, which underline the superiority of our approach. The machine learning models exhibit nonlinear pattern capture and responsiveness to market fluctuations. Insights into the relative significance of various variables and their effect on oil price movements in KSA are also provided by the sensitivity analysis. By demonstrating the usefulness of machine learning methods for oil price forecasting, particularly in the context of Saudi Arabia, this research adds to the body of knowledge already available. Our findings have important policy and market implications for oil price forecasting, benefiting policymakers, energy market participants, and investors. To improve the models’ ability to forecast the future, researchers may want to consider including more variables in their analyses, such as geopolitical developments and technology advances.

Generalizability and Out-of-Sample Predictive Ability of Associations Between Neuromelanin-Sensitive Magnetic Resonance Imaging and Psychosis in Antipsychotic-Free Individuals

The link between psychosis and dopaminergic dysfunction is established, but no generalizable biomarkers with clear potential for clinical adoption exist. To replicate previous findings relating neuromelanin-sensitive magnetic resonance imaging (NM-MRI), a proxy measure of dopamine function, to psychosis severity in antipsychotic-free individuals in the psychosis spectrum and to evaluate the out-of-sample predictive ability of NM-MRI for psychosis severity. This cross-sectional study recruited participants from 2019 to 2023 in the New York City area (main samples) and Mexico City area (external validation sample). The main samples consisted of 42 antipsychotic-free patients with schizophrenia, 53 antipsychotic-free individuals at clinical high risk for psychosis (CHR), and 52 matched healthy controls. An external validation sample consisted of 16 antipsychotic-naive patients with schizophrenia. NM-MRI contrast within a subregion of the substantia nigra previously linked to psychosis severity (a priori psychosis region of interest [ROI]) and psychosis severity measured using the Positive and Negative Syndrome Scale (PANSS) in schizophrenia and the Structured Interview for Psychosis-Risk Syndromes (SIPS) in CHR. The cross-validated performance of linear support vector regression to predict psychosis severity across schizophrenia and CHR was assessed, and a final trained model was tested on the external validation sample. Of the 163 included participants, 76 (46.6%) were female, and the mean (SD) age was 29.2 (10.4) years. In the schizophrenia sample, higher PANSS positive total scores correlated with higher mean NM-MRI contrast in the psychosis ROI (t37 = 2.24, P = .03; partial r = 0.35; 95% CI, 0.05 to 0.55). In the CHR sample, no significant association was found between higher SIPS positive total score and NM-MRI contrast in the psychosis ROI (t48 = -0.55, P = .68; partial r = -0.08; 95% CI, -0.36 to 0.23). The 10-fold cross-validated prediction accuracy of psychosis severity was above chance in held-out test data (mean r = 0.305, P = .01; mean root-mean-square error [RMSE] = 1.001, P = .005). External validation prediction accuracy was also above chance (r = 0.422, P = .046; RMSE = 0.882, P = .047). This study provided a direct ROI-based replication of the in-sample association between NM-MRI contrast and psychosis severity in antipsychotic-free patients with schizophrenia. In turn, it failed to replicate such association in CHR individuals. Most critically, cross-validated machine-learning analyses provided a proof-of-concept demonstration that NM-MRI patterns can be used to predict psychosis severity in new data, suggesting potential for developing clinically useful tools.

Design and Experiment of a Portable Near-Infrared Spectroscopy Device for Convenient Prediction of Leaf Chlorophyll Content.

This study designs a spectrum data collection device and system based on the Internet of Things technology, aiming to solve the tedious process of chlorophyll collection and provide a more convenient and accurate method for predicting chlorophyll content. The device has the advantages of integrated design, portability, ease of operation, low power consumption, low cost, and low maintenance requirements, making it suitable for outdoor spectrum data collection and analysis in fields such as agriculture, environment, and geology. The core processor of the device uses the ESP8266-12F microcontroller to collect spectrum data by communicating with the spectrum sensor. The spectrum sensor used is the AS7341 model, but its limited number of spectral acquisition channels and low resolution may limit the exploration and analysis of spectral data. To verify the performance of the device and system, this experiment collected spectral data of Hami melon leaf samples and combined it with a chlorophyll meter for related measurements and analysis. In the experiment, twelve regression algorithms were tested, including linear regression, decision tree, and support vector regression. The results showed that in the original spectral data, the ETR method had the best prediction effect at a wavelength of 515 nm. In the training set, RMSEc was 0.3429, and Rc2 was 0.9905. In the prediction set, RMSEp was 1.5670, and Rp2 was 0.8035. In addition, eight preprocessing methods were used to denoise the original data, but the improvement in prediction accuracy was not significant. To further improve the accuracy of data analysis, principal component analysis and isolation forest algorithm were used to detect and remove outliers in the spectral data. After removing the outliers, the RFR model performed best in predicting all wavelength combinations of denoised spectral data using PBOR. In the training set, RMSEc was 0.8721, and Rc2 was 0.9429. In the prediction set, RMSEp was 1.1810, and Rp2 was 0.8683.

A hybrid approach combining data envelopment analysis and recurrent neural network for predicting the efficiency of research institutions

The traditional data envelopment analysis (DEA) method relies solely on current and historical performance and is unable to predict future efficiency. To overcome this limitation, we propose a novel prediction model called the input–output memory network (IOMN), which extends the Recurrent Neural Network (e.g., Long Short-Term Memory (LSTM) and Gate Recurrent Unit (GRU) to forecast the input and output variables in future periods. We then combined the IOMN with the DEA-Malmquist index to evaluate the efficiency of Decision-Making Units (DMUs) from the past to the future. To demonstrate the effectiveness of our proposed model, we conducted a case study of 15 research institutions in the Chinese Academy of Sciences (CAS) and compared its performance with those of linear regression (LR) and support vector regression (SVR) methods. The comparative results show that the IOMN significantly outperformed both the LR and SVR methods. Finally, we fed the past and predicted future data into the DEA-Malmquist index to examine the productivity efficiency trends in research institutions over time. Our results indicate that the annual mean of total factor productivity (TFP) continued to fluctuate at approximately 1 during the observation period. In the future, the geometric mean of TFP will decline slightly by 2.3%, the geometric mean of efficiency change (EC) will decline by 5%, and the geometric mean of technical change (TC) will increase by 2.9%.