Linear Support Vector Machine Research Articles

Prediction of the health state of lithium-ion power batteries using machine learning

Faced with the increasingly urgent issues of energy depletion and environmental pollution, various countries are actively supporting the new energy vehicle industry, making electric vehicle technology a focus of widespread attention among researchers. The Battery Management System (BMS) plays a crucial role in overseeing the power battery's operational parameters, with the estimation of the State of Health (SOH) being a pivotal function. Accurate estimation of SOH can improve the utilization efficiency and endurance of power batteries, extend their service life, and help users achieve the best balance between system safety and economic benefits. Machine learning methods provide a new solution to the SOH estimation problem. Without analyzing the complex aging mechanisms inside the battery, online SOH estimation can be completed by learning from historical aging data. In this study, the lithium battery dataset provided by NASA is used and trained through multiple linear regression models and support vector machine models to predict the SOH of lithium-ion batteries. The results demonstrate the accuracy and reliability of both methods in predicting SOH. Simultaneously, the prediction results of different feature values are compared to obtain the most accurate combination of feature values.

A Productivity Prediction Method of Fracture-Vuggy Reservoirs Based on the PSO-BP Neural Network

Reservoir productivity prediction is a key component of oil and gas field development, and the rapid and accurate evaluation of reservoir productivity plays an important role in evaluating oil field development potential and improving oil field development efficiency. Fracture-vuggy reservoirs are characterized by strong heterogeneity, complex distribution, and irregular development, causing great difficulties in the efficient prediction of fracture-vuggy reservoirs’ productivity. Therefore, a PSO-BP fracture-vuggy reservoir productivity prediction model optimized by feature optimization was proposed in this paper. The Chatterjee correlation coefficient was used to select the appropriate combination of seismic attributes as the input of the prediction model, and we applied the PSO-BP model to predict oil wells’ production in a typical fracture-vuggy reservoir area of Tahe Oilfield, China, with the selected seismic attributes and compared the accuracy with that provided by the BP neural network, linear support vector machine, and multiple linear regression. The prediction results using the four models based on the test set showed that compared with the other three models, the MSE of the PSO-BP model increased by 23% to 62%, the RMSE increased by 12 to 38 percent, the MAE increased by 18 to 44 percent, the SSE increased by 23 to 62 percent, and the R-square value increased by 2 to 13 percent. This comparison proves that the PSO-BP neural network model proposed in this paper is suitable for the productivity prediction of fracture-vuggy reservoirs and has better performance, which is of guiding significance for the development and production of fracture-vuggy reservoirs.

Unveiling intrusions: explainable SVM approaches for addressing encrypted Wi-Fi traffic in UAV networks

AbstractUnmanned aerial vehicles (UAVs), also known as drones, have become instrumental in various domains, including agriculture, geographic information systems, media, logistics, security, and defense. These UAVs often rely on wireless communication networks for data transmission, making them vulnerable to cyberattacks. To address these challenges, it is necessary to detect potential threats by analyzing the encrypted Wi-Fi traffic data generated by UAVs. This study aimed to develop a linear SVM model that is enhanced with explainable artificial intelligence (XAI) techniques and fine-tuned using Bayesian optimization for intrusion detection systems (IDSs); the model is specifically designed to identify malware threats targeting UAVs. This research utilized encrypted Wi-Fi traffic data derived from three different UAV networks, namely, Parrot Bebop 1, DBPower UDI, and DJI Spark, while considering unidirectional and bidirectional communication flow modes. SVM-based intrusion detection models have been modeled on these datasets, identified their key features using the local interpretable model-agnostic explanations (LIME) technique, and conducted a cost analysis of the proposed modeling approach. The incorporation of the LIME method enabled to highlight the features that are highly indicative of cyberattacks and provided valuable insights into the importance of each feature in the context of intrusion detection. In conclusion, this interpretable IDS model, fine-tuned with Bayesian optimization, demonstrated its superiority over the state-of-the-art methods, proving its efficacy in detecting and mitigating threats to UAVs while offering a cost-effective solution.

Altered resting-state brain entropy in cerebral small vessel disease patients with cognitive impairment.

Cerebral small vessel disease (CSVD) is a primary vascular disease of cognitive impairment. Previous studies have predominantly focused on brain linear features. However, the nonlinear measure, brain entropy (BEN), has not been elaborated. Thus, this study is aim to investigate if BEN abnormalities could manifest in CSVD patients with cognitive impairment. 34 CSVD patients with cognitive impairment and 37 healthy controls (HCs) were recruited. Analysis of gray matter approximate entropy (ApEn) and sample entropy (SampEn) which are two indices of BEN were calculated. To explore whether BEN can provide unique information, we further performed brain linear methods, namely amplitude of low frequency fluctuation (ALFF) and regional homogeneity (ReHo), to observe their differences. The ratios of BEN/ALFF and BEN/ReHo which represent the coupling of nonlinear and linear features were introduced. Correlation analysis was conducted between imaging indices and cognition. Subsequently, the linear support vector machine (SVM) was used to assess their discriminative ability. CSVD patients exhibited lower ApEn and SamEn value in sensorimotor areas, which were correlated with worse memory and executive function. Additionally, the results of BEN showed little overlap with ALFF and ReHo in brain regions. Correlation analysis also revealed a relationship between the two ratios and cognition. SVM analysis utilizing BEN and its ratios as features achieved an accuracy of 74.64 % (sensitivity: 86.49 %; specificity: 61.76 %; and AUC: 0.82439). Our study reveals that the reduction of sensorimotor system complexity is correlated with cognition. BEN exhibits distinctive characteristics in brain activity. Combining BEN and the ratios can be new biomarkers to diagnose CSVD with cognitive impairment.

Molecular insights into programmed cell death in esophageal squamous cell carcinoma.

Esophageal squamous cell carcinoma (ESCC) is a deadly type of esophageal cancer. Programmed cell death (PCD) is an important pathway of cellular self-extermination and is closely involved in cancer progression. A detailed study of its mechanism may contribute to ESCC treatment. We obtained expression profiling data of ESCC patients from public databases and genes related to 12 types of PCD from previous studies. Hub genes in ESCC were screened from PCD-related genes applying differential expression analysis, machine learning analysis, linear support vector machine (SVM), random forest and Least Absolute Shrinkage and Selection Operator (LASSO) regression analysis. In addition, based on the HTFtarget and TargetScan databases, transcription factors (TFs) and miRNAs interacting with the hub genes were selected. The relationship between hub genes and immune cells were analyzed using the CIBERSORT algorithm. Finally, to verify the potential impact of the screened hub genes on ESCC occurrence and development, a series of in vitro cell experiments were conducted. We screened 149 PCD-related DEGs, of which five DEGs (INHBA, LRRK2, HSP90AA1, HSPB8, and EIF2AK2) were identified as the hub genes of ESCC. The area under the curve (AUC) of receiver operating characteristic (ROC) curve of the integrated model developed using the hub genes reached 0.997, showing a noticeably high diagnostic accuracy. The number of TFs and miRNAs regulating hub genes was 105 and 22, respectively. INHBA, HSP90AA1 and EIF2AK2 were overexpressed in cancer tissues and cells of ESCC. Notably, INHBA knockdown suppressed ECSS cell migration and invasion and altered the expression of important apoptotic and survival proteins. This study identified significant molecules with promising accuracy for the diagnosis of ESCC, which may provide a new perspective and experimental basis for ESCC research.

Cerebral hemodynamics as biomarkers for neuropathic pain in rats: a longitudinal study using a spinal nerve ligation model.

Neuropathic pain is one of the most challenging types of pain to diagnose and treat, a problem exacerbated by the lack of a quantitative biomarker. Recently, several clinical and preclinical studies have shown that neuropathic pain induces cerebral hemodynamic changes as a result of neuroplasticity in the brain. Our hypothesis in this study is that neuropathic pain leads to cerebral hemodynamic changes over postoperative time in a spinal nerve ligation (SNL) rat model, which has not been longitudinally explored previously. Furthermore, by identifying multiple regional hemodynamic features that are the most distinct between SNL and sham groups, where the sham group underwent only an incision without SNL, it may be possible to classify the SNL group regardless of when the onset of pain occurs. We investigate cerebral hemodynamic changes using dynamic susceptibility contrast magnetic resonance imaging in a rat model up to 28 days after ligating L5/L6 spinal nerves. We trained a linear support vector machine with relative cerebral blood volume data from different brain regions and found that the prediction model trained on the nucleus accumbens, motor cortex, pretectal area, and thalamus classified the SNL group and sham group at a 79.27% balanced accuracy, regardless of when the onset of pain occurred (SNL/sham: 60/45 data points). From the use of the SNL model without prior knowledge of the onset time of pain, the current findings highlight the potential of relative cerebral blood volume in the 4 highlighted brain regions as a biomarker for neuropathic pain.

Cerebral hemodynamics as biomarkers for neuropathic pain in rats: a longitudinal study using a spinal nerve ligation model.

Neuropathic pain is one of the most challenging types of pain to diagnose and treat, a problem exacerbated by the lack of a quantitative biomarker. Recently, several clinical and preclinical studies have shown that neuropathic pain induces cerebral hemodynamic changes as a result of neuroplasticity in the brain. Our hypothesis in this study is that neuropathic pain leads to cerebral hemodynamic changes over postoperative time in a spinal nerve ligation (SNL) rat model, which has not been longitudinally explored previously. Furthermore, by identifying multiple regional hemodynamic features that are the most distinct between SNL and sham groups, where the sham group underwent only an incision without SNL, it may be possible to classify the SNL group regardless of when the onset of pain occurs. We investigate cerebral hemodynamic changes using dynamic susceptibility contrast magnetic resonance imaging in a rat model up to 28 days after ligating L5/L6 spinal nerves. We trained a linear support vector machine with relative cerebral blood volume data from different brain regions and found that the prediction model trained on the nucleus accumbens, motor cortex, pretectal area, and thalamus classified the SNL group and sham group at a 79.27% balanced accuracy, regardless of when the onset of pain occurred (SNL/sham: 60/45 data points). From the use of the SNL model without prior knowledge of the onset time of pain, the current findings highlight the potential of relative cerebral blood volume in the 4 highlighted brain regions as a biomarker for neuropathic pain.

Permutation-invariant linear classifiers

AbstractInvariant concept classes form the backbone of classification algorithms immune to specific data transformations, ensuring consistent predictions regardless of these alterations. However, this robustness can come at the cost of limited access to the original sample information, potentially impacting generalization performance. This study introduces an addition to these classes—the permutation-invariant linear classifiers. Distinguished by their structural characteristics, permutation-invariant linear classifiers are unaffected by permutations on feature vectors, a property not guaranteed by other non-constant linear classifiers. The study characterizes this new concept class, highlighting its constant capacity, independent of input dimensionality. In practical assessments using linear support vector machines, the permutation-invariant classifiers exhibit superior performance in permutation experiments on artificial datasets and real mutation profiles. Interestingly, they outperform general linear classifiers not only in permutation experiments but also in permutation-free settings, surpassing unconstrained counterparts. Additionally, findings from real mutation profiles support the significance of tumor mutational burden as a biomarker.

Machine Learning-Assisted Exploration of Intrinsically Spin-Ordered Two-Dimensional (2D) Nanomagnets.

The existence of spontaneous spin-ordering in two-dimensional (2D) nanomagnets holds significant importance due to their several unique and promising properties that distinguish them from conventional 2D materials. In recent times, machine learning (ML) has emerged as a powerful tool for effectively exploring and identifying the optimal 2D materials for specific applications or properties within a limited span of time. Here, we have introduced ML-accelerated approaches to specifically estimate the properties, such as the HSE bandgap and magnetoanisotropic energy (MAE) of 2D magnetic materials. Supervised ML algorithms were employed to derive the descriptors that are capable of predicting the properties of intrinsic 2D magnetic materials. Furthermore, the feature selection score is also calculated to reduce the feature space complexity and improve the model accuracy. The input features were obtained from the C2DB database, and models were constructed using linear regression, Lasso, decision tree, random forest, XG Boost, and support vector machine algorithms. The random forest model predicted the HSE band gaps with an unprecedented low root-mean-square error (RMSE) of 0.22 eV, while the linear regression gives the best fit with RMSEs of 0.25 and 0.22 meV for the MAE(x) and MAE(y), respectively. Therefore, the integration of interpretable analytical models with density functional theory offers a swift and reliable approach for uncovering the properties of intrinsic 2D magnetic materials. This collaborative methodology not only ensures speed in analysis but also enriches the material space.

Machine Learning-Assisted Exploration of Intrinsically Spin-Ordered Two-Dimensional (2D) Nanomagnets.

The existence of spontaneous spin-ordering in two-dimensional (2D) nanomagnets holds significant importance due to their several unique and promising properties that distinguish them from conventional 2D materials. In recent times, machine learning (ML) has emerged as a powerful tool for effectively exploring and identifying the optimal 2D materials for specific applications or properties within a limited span of time. Here, we have introduced ML-accelerated approaches to specifically estimate the properties, such as the HSE bandgap and magnetoanisotropic energy (MAE) of 2D magnetic materials. Supervised ML algorithms were employed to derive the descriptors that are capable of predicting the properties of intrinsic 2D magnetic materials. Furthermore, the feature selection score is also calculated to reduce the feature space complexity and improve the model accuracy. The input features were obtained from the C2DB database, and models were constructed using linear regression, Lasso, decision tree, random forest, XG Boost, and support vector machine algorithms. The random forest model predicted the HSE band gaps with an unprecedented low root-mean-square error (RMSE) of 0.22 eV, while the linear regression gives the best fit with RMSEs of 0.25 and 0.22 meV for the MAE(x) and MAE(y), respectively. Therefore, the integration of interpretable analytical models with density functional theory offers a swift and reliable approach for uncovering the properties of intrinsic 2D magnetic materials. This collaborative methodology not only ensures speed in analysis but also enriches the material space.

Diagnosing Breast Cancer Using AI: A Comparison of Deep Learning and Traditional Machine Learning Methods

Breast cancer remains a significant health concern globally, with early detection being crucial for effective treatment. In this study, we explore the predictive power of various diagnostic features in breast cancer using machine learning techniques. We analyzed a dataset comprising clinical measurements of mammograms from 569 patients, including mean radius, texture, perimeter, area, and smoothness, alongside the diagnosis outcome. Our methodology involves preprocessing steps such as handling missing values and removing duplicates, followed by a correlation analysis to identify and eliminate highly correlated features. Subsequently, we train eight machine learning models, including Logistic Regression (LR), K-Nearest Neighbors (K-NN), Linear Support Vector Machine (SVM), Kernel SVM, Naïve Bayes, Decision Trees Classifier (DTC), Random Forest Classifier (RFC), and Artificial Neural Networks (ANN), to predict the diagnosis based on the selected features. Through comprehensive evaluation metrics such as accuracy and confusion matrices, we assess the performance of each model. Our findings reveal promising results, with 6 out of 8 models achieving high accuracy (>90%), with ANN having the highest accuracy in diagnosing breast cancer based on the selected features. These results underscore the potential of machine learning algorithms in aiding early breast cancer diagnosis and highlight the importance of feature selection in improving predictive performance.

P-443 An association between olfaction and unexplained recurrent pregnancy loss

Abstract Study question Is there a male body-odor associated with unexplained recurrent pregnancy loss (uRPL)? Summary answer The body-odor of men from uRPL couples may have different chemical composition than control men. What is known already Recurrent pregnancy loss is defined as 2-3 consecutive pregnancy losses, affecting about 1% of all couples, and in about half of them, the reason for the pregnancy losses in unexplained (uRPL). In our previously published study, we found that women who experienced uRPL have altered perceptual and brain responses to men’s body-odors in comparison to control women. This suggests a possible link between uRPL and the olfactory system, resonating with the Bruce effect in mice. In the Bruce effect, the particularities of male body-odor are also a factor in the effect. Study design, size, duration We set out to ask whether the body-odor (BO) of men in uRPL is different from the BO of control men. To test this, we used two main approaches: have women smell BOs from uRPL-men and control-men and rate the perceived odor; and sample the BOs using a machine (electronic nose) and test if the composition of the BOs is objectively different. Participants/materials, setting, methods We collected BOs from spouses of uRPL and control women. We recruited women with uRPL, control women (with no history of pregnancy losses) and nulliparous women to sniff the BOs and rate them for perceived intensity, pleasantness, sexual attraction, and fertility. We then used an electronic nose (eNose, Airsense) to sample the BOs and used a Linear SVM classifier on this data, to try and classify the BOs to the two groups. Main results and the role of chance Twenty-one women with uRPL and 24 control women sniffed and rated 34 BO jars (17 uRPL-men). We found that uRPL-men BO was rated as more pleasant, sexually attractive and fertile than control men (rmANOVAs for each parameter but intensity revealed a significant effect of male group (all F(1,43)>14.24, all p < 0.001), no women-group effect and no interactions). We then recruited 51 nulliparous women, not related to the original study, to do the same task, and the results replicated: nulliparous women rated uRPL-men’s BO significantly more pleasant, sexually attractive and fertile than control men’s BO (all t(50)>2.88, all p < =0.006), while the intensity was not different (t(50)=0.87, p = 0.38). We then used a PEN3 eNose to sample 37 male BOs (18 uRPL). The PEN3 eNose contains 10 different metal oxide sensors, and each sensor is coated in a unique material that makes it sensitive to different sets of chemical compounds. Based on the data from the eNose, a Linear SVM classifier successfully classified the odors to uRPL-men or control-men at 69.9% accuracy in a five-fold cross-validation test (p < 0.001 estimated by repeating the process 1000 times and shuffling the labels). Limitations, reasons for caution This study shows an association between the body-odor of men and uRPL, however it shows a correlative connection (not causative). Therefore, the interpretation for these current results are limited. Wider implications of the findings These initial results suggest that uRPL-men’s and control-men’s BO have different chemical composition. This implies a possible contribution of men to the effect we observed in our previously published study, and combined, further strengthens a link between uRPL and the olfactory system that we continue to investigate. Trial registration number not applicable

Assessment of Mycological Possibility Using Machine Learning Models for Effective Inclusion in Sustainable Forest Management

The integral role of wild fungi in ecosystems, including provisioning, regulating, cultural, and supporting services, is well recognized. However, quantifying and predicting wild mushroom yields is challenging due to spatial and temporal variability. In Mediterranean forests, climate-change-induced droughts further impact mushroom production. Fungal fruiting is influenced by factors such as climate, soil, topography, and forest structure. This study aims to quantify and predict the mycological potential of Lactarius deliciosus in sustainably managed Mediterranean pine forests using machine learning models. We utilize a long-term dataset of Lactarius deliciosus yields from 17 Pinus pinaster plots in Soria, Spain, integrating forest-derived structural data, NASA Landsat mission vegetation indices, and climatic data. The resulting multisource database facilitates the creation of a two-stage ‘mycological exploitability’ index, crucial for incorporating anticipated mycological production into sustainable forest management, in line with what is usually done for other uses such as timber or game. Various Machine Learning (ML) techniques, such as classification trees, random forest, linear and radial support vector machine, and neural networks, were employed to construct models for classification and prediction. The sample was always divided into training and validation sets (70-30%), while the differences were found in terms of Overall Accuracy (OA). Neural networks, incorporating critical variables like climatic data (precipitation in January and humidity in November), remote sensing indices (Enhanced Vegetation Index, Green Normalization Difference Vegetation Index), and structural forest variables (mean height, site index and basal area), produced the most accurate and unbiased models (OAtraining = 0.8398; OAvalidation = 0.7190). This research emphasizes the importance of considering a diverse array of ecosystem variables for quantifying wild mushroom yields and underscores the pivotal role of Artificial Intelligence (AI) tools and remotely sensed observations in modeling non-wood forest products. Integrating such models into sustainable forest management plans is crucial for recognizing the ecosystem services provided by them.

Assessing kiwifruit quality in storage through machine learning

AbstractToday, diets rich in fruits and vegetables are highly recommended since they contribute to health. The high deterioration rate of fruits distinguishes them from other crops. This study aimed to evaluate the effects of various storage conditions on some quality attributes of kiwifruit through machine learning (ML) using support vector machine (SVM) models. Kiwifruits were subjected to quasi‐static loading and coated with different coatings, such as grape, date, and mulberry syrups. Then, the coated kiwifruits were stored at humidity levels of 90% and 95% in completely dark and bright environments with a Compact fluorescent lamp (CFL) bulb for 5, 10, and 15 days. Once the storage period had been completed, quality attributes of the kiwifruit, including antioxidant content, phenolic content, total soluble solids (TSS), pH, and firmness were measured. Each test was performed three times. The numerical results were analyzed through an ML approach using an SVM model on MATLAB. To predict the physical properties of kiwifruit using storage conditions and vice versa, it was found that the most accurate SVM model with a linear kernel predicted the weight loss of kiwifruit based on storage conditions, with the coefficient of determination (R2) being 0.54. To predict the biochemical properties using the storage conditions and vice versa, it was found that kiwifruit firmness was most accurately predicted by the SVM model with the Gaussian kernel, with an R2 of 0.70. Moreover, humidity and storage duration were modeled by SVMs with linear kernels, calculating the coefficients of determination to be 0.39 and 0.90, respectively. To predict biochemical properties using physical properties and vice versa, it was observed that the weight loss was more accurately predicted by an SVM with a linear kernel, with an R2‐value of 0.76. Reliable results were not obtained for further research for the other modeled parameters using an SVM approach.Practical ApplicationsIt was found that light was most accurately predicted by the linear SVM. Storage conditions revealed SVM (linear kernel) accurately predicting kiwifruit weight loss. Linear and Gaussian SVMs accurately modeled phenolic and antioxidant content, R2‐values: 0.73 and 0.34, respectively.

Deactivation and collective phasic muscular tuning for pointing direction: Insights from machine learning

Arm movements in our daily lives have to be adjusted for several factors in response to the demands of the environment, for example, speed, direction or distance. Previous research has shown that arm movement kinematics is optimally tuned to take advantage of gravity effects and minimize muscle effort in various pointing directions and gravity contexts. Here we build upon these results and focus on muscular adjustments. We used Machine Learning to analyze the ensemble activities of multiple muscles recorded during pointing in various directions. The advantage of such a technique would be the observation of patterns in collective muscular activity that may not be noticed using univariate statistics. By providing an index of multimuscle activity, the Machine Learning (ML) analysis brought to light several features of tuning for pointing direction. In attempting to trace tuning curves, all comparisons were done with respects to pointing in the horizontal, gravity free plane. We demonstrated that tuning for direction does not take place in a uniform fashion but in a modular manner in which some muscle groups play a primary role. The antigravity muscles were more finely tuned to pointing direction than the gravity muscles. Of note, was their tuning during the first half of downward pointing. As the antigravity muscles were deactivated during this phase, it supported the idea that deactivation is not an on-off function but is tuned to pointing direction. Further support for the tuning of the negative portions of the phasic EMG was provided by the observation of progressively improving classification accuracies with increasing angular distance from the horizontal. We also demonstrated that the durations of these negative phases, without information on their amplitudes, is tuned to pointing directions. Overall, these results show that the motor system tunes muscle commands to exploit gravity effects and reduce muscular effort. It quantitatively demonstrates that phasic EMG negativity is an essential feature of muscle control. The ML analysis was done using Linear Discriminant analysis (LDA) and Support Vector Machines (SVM). The two led to the same conclusions concerning the movements being investigated, hence showing that the former, computationally inexpensive technique is a viable tool for regular investigation of motor control.

EEG-based driving intuition and collision anticipation using joint temporal-frequency multi-layer dynamic brain network.

Intuition plays a crucial role in human driving decision-making, and this rapid and unconscious cognitive process is essential for improving traffic safety. We used the first proposed multi-layer network analysis method, "Joint Temporal-Frequency Multi-layer Dynamic Brain Network" (JTF-MDBN), to study the EEG data from the initial and advanced phases of driving intuition training in the theta, alpha, and beta bands. Additionally, we conducted a comparative study between these two phases using multi-layer metrics as well as local and global metrics of single layers. The results show that brain region activity is more stable in the advanced phase of intuition training compared to the initial phase. Particularly in the alart state task, the JTF-MDBN demonstrated stronger connection strength. Multi-layer network analysis indicates that modularity is significantly higher for the non-alert state task than the alert state task in the alpha and beta bands. In the W4 time window (1 second before a collision), we identified significant features that can differentiate situations where a car collision is imminent from those where no collision occurs. Single-layer network analysis also revealed statistical differences in node strength and local efficiency for some EEG channels in the alpha and beta bands during the W4 and W5 time windows. Using these biomarkers to predict vehicle collision risk, the classification accuracy of a linear kernel SVM reached up to 87.5%, demonstrating the feasibility of predicting driving collisions through brain network biomarkers. These findings are important for the study of human intuition and the development of brain-computer interface-based intelligent driving hazard perception assistance systems.

Identification of male schizophrenia patients using brain morphology based on machine learning algorithms.

Schizophrenia is a severe psychiatric disease, and its prevalence is higher. However, diagnosis of early-stage schizophrenia is still considered a challenging task. To employ brain morphological features and machine learning method to differentiate male individuals with schizophrenia from healthy controls. The least absolute shrinkage and selection operator and t tests were applied to select important features from structural magnetic resonance images as input features for classification. Four commonly used machine learning algorithms, the general linear model, random forest (RF), k-nearest neighbors, and support vector machine algorithms, were used to develop the classification models. The performance of the classification models was evaluated according to the area under the receiver operating characteristic curve (AUC). A total of 8 important features with significant differences between groups were considered as input features for the establishment of classification models based on the four machine learning algorithms. Compared to other machine learning algorithms, RF yielded better performance in the discrimination of male schizophrenic individuals from healthy controls, with an AUC of 0.886. Our research suggests that brain morphological features can be used to improve the early diagnosis of schizophrenia in male patients.

Real-time ozonation monitoring and control in wastewater tertiary treatment: An ultraviolet-visible monitoring approach

To address the challenge of refractory organics removal in wastewater tertiary treatment, this study investigates the application of ozonation, coupled with Ultraviolet-Visible (UV–Vis) spectroscopy, for enhanced tertiary treatment in a wastewater treatment plant (WWTP) in Qingdao, China. Our approach integrates ozonation with real-time UV–Vis spectral monitoring to precisely control ozone dosing, targeting the effective degradation of persistent organics characterized by high Chemical Oxygen Demand (COD) values. Through the deployment of mathematical models, including Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM), we developed a robust two-step ozone dosing control model. The model's efficacy is validated by its ability to predict the need for ozonation with a high degree of accuracy (94.29 % for LDA), significantly optimizing the ozonation process. Key findings indicate that this method not only achieves substantial removal of recalcitrant organics (with COD removal rates varying between 16 % and 71 %) but also offers considerable energy savings and operational cost reductions by adjusting ozone dosing in real-time based on water quality data. This study presents a novel, sustainable approach to improving WWTP efficiency and compliance, showcasing the potential of integrating advanced oxidation processes with precision monitoring techniques for environmental protection and water reuse initiatives.

COVID-19's influence on Karachi stock exchange: A comparative machine learning algorithms study for forecasting

The COVID-19 pandemic has great effects for economies internationally. This study studies the interconnection between COVID-19 metrics and Pakistan's premier stock exchange, the Karachi Stock Exchange (KSE) with the object of identifying the most effective machine learning (ML) model for predicting KSE developments in the pandemic. Our investigation periods the peak COVID-19 period from March 1, 2020, to November 26, 2021, applying data from both the KSE 100 index and COVID-19 associated variables. Five various ML methods were applied involving Linear Regression (LR), K-Nearest Neighbors (KNN), Random Forest (RF), Regression Tree (Rtree), and Support Vector Machine (SVM) and measured their performance employing critical accuracy metrics such as Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE), Mean Absolute Error (MAE), and R-squared (R2). The outcomes discover that the RF model outperformed its equivalents realizing an R2 of 0.91 with k = 5. These results conflict with a previous study that supported a negative impact of COVID-19 on improved stock markets. The visions from this study can assist investors in managing strategic investment decisions and assist policymakers in making measures to reduce the pandemic's effects on the stock market.

Machine learning approach to predict venous thromboembolism among patients undergoing multi-level spinal posterior instrumented fusion.

The absence of consensus for prophylaxis of venous thromboembolism (VTE) in spine surgery underscores the importance of identifying patients at risk. This study incorporated machine learning (ML) models to assess key risk factors of VTE in patients who underwent posterior spinal instrumented fusion. Data was collected from the IBM MarketScan Database [2009-2021] for patients ≥18 years old who underwent spinal posterior instrumentation (3-6 levels), excluding traumas, malignancies, and infections. VTE incidence (deep vein thrombosis and pulmonary embolism) was recorded 90-day post-surgery. Risk factors for VTE were investigated and compared through several ML models including logistic regression, linear support vector machine (LSVM), random forest, XGBoost, and neural networks. Among the 141,697 patients who underwent spinal fusion with posterior instrumentation (3-6 levels), the overall 90-day VTE rate was 3.81%. The LSVM model demonstrated the best prediction with an area under the curve (AUC) of 0.68. The most important features for prediction of VTE included remote history of VTE, diagnosis of chronic hypercoagulability, metastatic cancer, hemiplegia, and chronic renal disease. Patients who did not have these five key risk factors had a 90-day VTE rate of 2.95%. Patients who had an increasing number of key risk factors had subsequently higher risks of postoperative VTE. The analysis of the data with different ML models identified 5 key variables that are most closely associated with VTE. Using these variables, we have developed a simple risk model with additive odds ratio ranging from 2.80 (1 risk factor) to 46.92 (4 risk factors) over 90 days after posterior spinal fusion surgery. These findings can help surgeons risk-stratify their patients for VTE risk, and potentially guide subsequent chemoprophylaxis.