SVM Model Research Articles

Feasibility and potential of terahertz spectral and imaging technology for Apple Valsa canker detection: A preliminary investigation

Apple Valsa canker (AVC) caused by the Ascomycete Valsa mali, seriously constrains the production and quality of apple fruits. The symptomless incubation characteristics of Valsa mali make it highly challenging to detect AVC at an early infection stage. After infecting the wound of apple bark, the pathogenic hyphae of AVC will expand and colonize the phloem tissue. Meanwhile, various enzymes and toxic substances released by hyphae cause the decomposition of cellulose and lignin, and the generation of poisonous secondary metabolites in bark tissue. However, these early symptoms of AVC are invisible from the bark’s appearance. Fortunately, Terahertz Spectral Imaging (ThzSI) technology with the advantage of penetrating, and fingerprinting is promising for detecting hidden or slight symptoms of the fungal infection. This study is a preliminary investigation of terahertz frequency-domain spectra for AVC in the early stage of infection. Healthy and two-week-infected apple tree branches were prepared for capturing ThzS images, and the spectral data were preprocessed by Multivariate scattering correction (MSC), Savitzky-Golay convolution smoothing (SG), and standard normal variate (SNV) respectively to remove data noise and improve data quality. Principal component analysis (PCA), competitive adaptive reweighted sampling (CARS), and random frog (RFROG) were employed to extract the spectral feature bands to eliminate redundant data and improve computational efficiency. Machine learning models were established based on the spectral features to detect AVC at an early infection stage, where 11 of them exhibited the best performance with F1-score of 99.72%. To further explore disease information in spatial spectra, imaging data were acquired using terahertz imaging technology. Based on imaging data, pseudo-color imaging, histogram equalization, and Otsu segmentation were employed to visualize early infection areas in apple barks. Furthermore, histogram feature (HF), shape feature (SF), and local binary pattern (LBP) extracted from terahertz spectral images were utilized to establish the SVM, RF, and KNN models. HF-SF-KNN and HF-SF-LBP-KNN with the best performance achieved F1-score of 98.82%. This study presents a preliminary application of terahertz spectral and imaging technology for early-stage AVC detection and demonstrates its feasibility. Additionally, it provides a new way to detect AVC, which expands the application of ThzSI technology in tree disease detection in orchards and lays the foundation for further research.

Recognition Of Digits From EEG Signals: An Innovative Approach

Communicating with computers through thought has been a remarkable achievement in recent years. This was made possible by the use of Electroencephalography (EEG). Brain-computer interface (BCI) relies heavily on Electroencephalography (EEG) signals for communication between humans and computers. With the advent of deep learning, many studies recently applied these techniques to EEG data to perform various tasks like emotion recognition, motor imagery classification, sleep analysis, and many more. This study proposes a methodological combination of EEG signal processing techniques and SVM models for the classification of digit. Also, it explores DCT and LDA techniques for feature extraction and selection. As a result, the proposed classification pipeline achieves comparable performance with the existing methods.

Imbalanced Data NearMiss for Comparison of SVM and Naive Bayes Algorithms

The study aims to improve the diagnosis, management, and prevention of HIV/AIDS by using classification algorithms. The dataset used consists of 707,379 records and 89 columns. Data preprocessing includes removing irrelevant attributes, handling inconsistencies, and balancing the data using the NearMiss method, resulting in a balanced proportion of reactive and non-reactive HIV cases. Once the data is balanced, it is split into several ratios: 60:40, 70:30, 80:20, and 90:10. The classification models used in this study are Naive Bayes and SVM. The models are evaluated using the metrics Accuracy, Precision, Recall, and F1-Score. The results show that the SVM model achieves the highest accuracy of 82.6% with a 90:10 data split at a 6-fold value, and 82.2% with a 60:40 data split at a 5-fold value. On the other hand, Naive Bayes achieves the highest accuracy of 61.1% with a 60:40 data split.

Machine learning ellipsometry as a sensitive diagnostic tool to study reproductive biology in Zika virus infected murine models

Machine-learning spectroscopy is a recent scientific and fast-growing area where specific machine-learning solutions are used to process spectroscopic data beyond traditional physical modeling. Here, several machine learning models are optimized and trained for processing highly sensitive broadband variable angle spectroscopic ellipsometry measurements as a new tool in reproductive biology. This new method is applied to classify semen samples obtained from male offspring from ZIKV-infected and uninfected murine models. The method is label-free, cost-effective, simple, and reaches excellent performance. The combination of spectroscopic depolarization degree data with a well-optimized and trained SVM model resulted in the excellent performance of AUROC = 0.99, accuracy = 92%, specificity = 87% and sensibility = 97%. Optical modeling of ellipsometry spectra with Kramers–Kronigconsistent B-splines that takes care of incoherent reflections in the samples allowed for the extraction of the average semen sample refraction index for each class, revealing small differences that were attributed to the observed semen head defects, protamination failure, and DNA fragmentation.

Comparative analysis of biomechanical patterns in sprinting: A machine learning approach to optimize running performance in track athletes

Athletes’ success in field and track competitions has been reported to be determined by their sprinting skills. Therefore, it is crucial to understand what biomechanical and physiological factors contribute to the most effective sprinting attributes. The scientific research on sprint evaluation has predominantly dealt with discrete metrics simultaneously, avoiding the interplay between multiple factors as the sprint progresses. Incorporating all the factors that could potentially influence the impact of excellent sprint ability is the primary objective of the present study. This research investigates the biomechanics of sprinting using a Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) hybrid approach, focusing mainly on factors like stride length, ground reaction forces, joint angles, and muscle activation patterns. The hybrid Machine Learning (ML) model accurately identifies between the two groups, and the results indicate that sprinters performing at the national level have more extended movements, higher reaction time to ground forces, and improved joint angles. The research project set up a 20-meter track for the race, and 30 participants, divided 50-50 between two distinct groups that included comparable college-level and national-level performers, participated. With a 92.4% accuracy, 90.2% precision, and 90.9% F1 score, the hybrid approach performed better than standard models in predicting optimum sprinting patterns. The higher efficiency is caused by phase-specific changes that the model unattended, such as enhanced knee angles and joint accelerated motion in the swing phase. In comparison, the SVM model, though respectable, lags behind with an accuracy of 85.7% and a lower precision and recall (82.4% and 80.9%, respectively). The RF model performed better than SVM with an accuracy of 88.1% and a balanced F1-score of 86.8% but still fell short of the CNN-LSTM hybrid. The standalone LSTM model performed relatively well, with an accuracy of 89.3% and an F1 score of 88.1%, showing its capability but still not matching the hybrid model’s performance.

Carbon dioxide evaporation heat transfer coefficient prediction in porous media using Machine learning algorithms based on experimental data

The prediction of the internal heat transfer coefficient during evaporation is vital for vapor-compression refrigeration and closed-loop power cycles. Accurate measurements and understanding of CO2 heat transfer in porous evaporators are essential for optimal system design across various operating conditions. This study utilizes a reference dataset derived from previous experiments that investigated the impact of porous evaporators on CO2′s internal heat transfer coefficient under sub-critical conditions, employing gravel sand as the porous medium. The dataset encompasses key factors: gravel sand porosities ranging from 39.8 % to 44.5 %, evaporator inlet pressures between 3700 and 4300 kPa, CO2 mass flow rates from 10.7x10-5–18x10-5kg.s−1, and porous tube effective diameters spanning 1.53 x10-3–3.4x10-3m. Employing three machine learning techniques (SVM, GPR, OBEM), the study predicts the internal heat transfer coefficient using regression models. The models’ predictions are analyzed and compared to expected values for validation, evaluating their performance using four statistical criteria. Results indicate SVM, GPR, and OBEM models achieved RMSEs of 1.5471, 1.8212, and 3.6978, respectively, while MAE errors were 1.1479, 1.2418, and 2.9787, respectively. Comparison with the dimensional analysis method reveals the effectiveness of the proposed models in accurately predicting internal heat transfer coefficients. The models exhibit low uncertainty and maintain prediction quality on an extended dataset without overfitting concerns. Overall, this research contributes valuable insights for designing heat exchangers and systems in vapor-compression refrigeration and closed-loop power cycles.

Deep bone oncology Diagnostics: Computed tomography based Machine learning for detection of bone tumors from breast cancer metastasis

PurposeThe objective of this study is to develop a novel diagnostic tool using deep learning and radiomics to distinguish bone tumors on CT images as metastases from breast cancer. By providing a more accurate and reliable method for identifying metastatic bone tumors, this approach aims to significantly improve clinical decision-making and patient management in the context of breast cancer. MethodsThis study utilized CT images of bone tumors from 178 patients, including 78 cases of breast cancer bone metastases and 100 cases of non-breast cancer bone metastases. The dataset was processed using the Medical Image Segmentation via Self-distilling TransUNet (MISSU) model for automated segmentation. Radiomics features were extracted from the segmented tumor regions using the Pyradiomics library, capturing various aspects of tumor phenotype. Feature selection was conducted using LASSO regression to identify the most predictive features. The model’s performance was evaluated using ten-fold cross-validation, with metrics including accuracy, sensitivity, specificity, and the Dice similarity coefficient. ResultsThe developed radiomics model using the SVM algorithm achieved high discriminatory power, with an AUC of 0.936 on the training set and 0.953 on the test set. The model’s performance metrics demonstrated strong accuracy, sensitivity, and specificity. Specifically, the accuracy was 0.864 for the training set and 0.853 for the test set. Sensitivity values were 0.838 and 0.789 for the training and test sets, respectively, while specificity values were 0.896 and 0.933 for the training and test sets, respectively. These results indicate that the SVM model effectively distinguishes between bone metastases originating from breast cancer and other origins. Additionally, the average Dice similarity coefficient for the automated segmentation was 0.915, demonstrating a high level of agreement with manual segmentations. ConclusionThis study demonstrates the potential of combining CT-based radiomics and deep learning for the accurate detection of bone metastases from breast cancer. The high-performance metrics indicate that this approach can significantly enhance diagnostic accuracy, aiding in early detection and improving patient outcomes. Future research should focus on validating these findings on larger datasets, integrating the model into clinical workflows, and exploring its use in personalized treatment planning.

Utilizing an integrated bioinformatics and machine learning approach to uncover biomarkers linking ulcerative colitis to purine metabolism-related genes

BackgroundUlcerative colitis (UC) is an increasing incidence of inflammatory disorder in the colon mucosa. One of the current research focuses is the alteration of metabolic networks in UC. One of the important aspects of this metabolic shift is the expression of purine metabolism genes (PMGs) vital for nucleic acid synthesis. Nevertheless, the precise function of PMGs in the pathophysiology of UC is not yet fully known. MethodsTo this end, this study used state-of-the-art bioinformatics tools and approaches to discover and confirm the PMGs involved in UC. All the 114 candidate PMGs were compared for their expression levels. GSEA and GSVA were applied to define the functional and pathway implications of these PMGs. Lasso regression and SVM-RFE approaches were used for the identification of hub genes and to assess the diagnostic potential of eight PMGs in UC classification. The relationship between these critical PMGs and clinical features was also systematically evaluated as well. The expression levels of these eight PMGs were validated using datasets GSE206285 and GSE179285. ResultsUsing bioinformatics and machine learning, this work seeks to establish the involvement of PMGs in UC. From the LASSO and SVM models, 114 DE PMGs were selected and investigated to build a stable predictive model. Based on these studies, the following genes: IMPDH1, GUK1, POLE3, ADCY3, ADCY4, PDE6B, PNPT1 and PDE4D were suggested as potential biomarkers of UC. Gene ontology enrichment analysis revealed that these genes are implicated in the biological processes of particular relevance to immune and inflammatory responses. The study also provided a lot of information on the interaction between immune cells and PMGs indicating that these genes may control some immune-related pathways in UC. Moreover, drug-gene interaction analysis presents potential therapeutic opportunities for potential drug targets which were further confirmed through molecular docking. Mendelian randomization analysis revealed that ADCY4 and PDAZN are involved in PMG-related processes, thus opening new possibilities for treatment. ConclusionsThis work reveals eight PMGs closely related to UC and provides new perspectives on possible markers of this inflammatory disease. These findings not only increase the understanding of the pathogenesis of UC but also offer potential for improving the surveillance of disease and its progression.

Constructing a Predictive Model for High School Students' Enrolment Results

Nowadays, data-informed decision-making can assist high-school educational decision-making, especially student test scores, and further education data, then these data can be used to inform decision-making in schools and boost overall school performance. We aimed to assess the relationships among high school students' admission scores, academic performance at school, and psychological tests in the school system. The relationships were used to predict the departmental fields and universities that students would select for advanced studies in the future. This research will utilize data mining algorithms, including Naïve Bayes, SVM, and Neural Network classifiers, to extract and analyze hidden patterns in students' academic records and credentials. When the Bayesian Network model was used to predict whether a student's university is public or private, our results showed 78.46% of the predicted results. Predicting the accuracy of the top three departmental fields, the SVM model achieved the highest performance with an accuracy of 69.77% .Given that students' academic performance varies across high schools, each school should develop its customized predictive model using only its students’ data. This will help students believe in and pursue their interests.

Comparative Analysis of Machine Learning Algorithms for Used Car Price Prediction

After 2021, over 90 million passenger automobiles were produced, marking a significant increase in auto production. This growth has led to a flourishing used car market, which has become a highly lucrative sector. One of the most critical and fascinating areas of research within this market is automobile price prediction. Accurate price prediction models can greatly benefit buyers, sellers, and businesses in the used car industry. This paper presents a detailed comparative analysis of two supervised machine learning models: K-Nearest Neighbour and Support Vector Machine regression techniques, to predict used car prices. We utilized a comprehensive dataset of used cars sourced from the Kaggle website for training and testing our models. The K Nearest Neighbour algorithm is known for its simplicity and effectiveness in regression tasks. On the other hand, the Support Vector Machine regression technique uses a different approach, finding the optimal hyperplane that best fits the data. Both methods have their strengths and weaknesses, which we explored in this study. Our results indicated that both KNN and SVM models performed well in predicting used car prices, but with slight variations in accuracy. Consequently, the suggested models fit as the optimum models and have an accuracy of about 83 percent for KNN and 80 percent for SVM. The results indicate that the KNN model slightly outperforms the SVM model in predicting used car prices.

Rapid and accurate identification of Gastrodia elata Blume species based on FTIR and NIR spectroscopy combined with chemometric methods

Different varieties of Gastrodia elata Blume (G. elata Bl.) have different qualities and different contents of active ingredients, such as polysaccharide and gastrodin, and it is generally believed that the higher the active ingredients, the better the quality of G. elata Bl. and the stronger the medicinal effects. Therefore, effective identification of G. elata Bl. species is crucial and has important theoretical and practical significance. In this study, first unsupervised PCA and t-SNE are established for data visualisation, follow by traditional machine learning (PLS-DA, OPLS-DA and SVM) models and deep learning (ResNet) models were established based on the fourier transform infrared (FTIR) and near infrared (NIR) spectra data of three G. elata Bl. species. The results show that PLS-DA, OPLS-DA and SVM models require complex preprocessing of spectral data to build stable and reliable models. Compared with traditional machine learning models, ResNet models do not require complex spectral preprocessing, and the training and test sets of ResNet models built based on raw NIR and low-level data fusion (FTIR + NIR) spectra reach 100 % accuracy, the external validation set based on low-level data fusion reaches 100 % accuracy, and the external validation set based on NIR has only one sample classification error and no overfitting.

Susceptibility assessment of multi-hazards using random forest—back propagation neural network coupling model: a Hangzhou city case study

As the demand for regional geological disaster risk assessments in large cities continues to rise, our study selected Hangzhou, one of China’s megacities, as a model to evaluate the susceptibility to two major geological hazards in the region: ground collapse and ground subsidence. Given that susceptibility assessments for such disasters mainly rely on knowledge-driven models, and data-driven models have significant potential for application, we proposed a high-accuracy Random Forest—Back Propagation Neural Network Coupling Model. By using nine evaluation factors selected based on field surveys and expert recommendations, along with disaster data, the model's predictive results indicate a 3–40% improvement in model performance metrics such as AUC, accuracy, precision, recall, and F1-score, compared to single models and traditional SVM and logistic regression models. Ultimately, using the predictive results of this model, we created susceptibility maps for individual disasters and developed a muti-hazards susceptibility map by employing the expert weight discrimination method and the overlay evaluation method. Furthermore, we discussed the feature importance in the prediction process. Our study validated the feasibility of using advanced machine learning models for urban geological disaster assessment, providing a replicable template for other cities.

Development of an AI-Based Predictive Algorithm for Early Diagnosis of High-Risk Dementia Groups among the Elderly: Utilizing Health Lifelog Data.

This study aimed to develop a predictive algorithm for the early diagnosis of dementia in the high-risk group of older adults using artificial intelligence technologies. The objective is to create an accessible diagnostic method that does not rely on traditional medical equipment, thereby improving the early detection and management of dementia. Lifelog data from wearable devices targeting this high-risk group were collected from the AI Hub platform. Various indicators from these data were analyzed to develop a dementia diagnostic model. Machine learning techniques such as Logistic Regression, Random Forest, LightGBM, and Support Vector Machine were employed. Data augmentation techniques were applied to address data imbalance, thereby enhancing the model performance. Data augmentation significantly improved the model's accuracy in classifying dementia cases. Specifically, in gait data, the SVM model performed with an accuracy of 0.879. In sleep data, a Logistic Regression was performed, yielding an accuracy of 0.818. This indicates that the lifelog data can effectively contribute to the early diagnosis of dementia, providing a practical solution that can be easily integrated into healthcare systems. This study demonstrates that lifelog data, which are easily collected in daily life, can significantly enhance the accessibility and efficiency of dementia diagnosis, aiding in the effective use of medical resources and potentially delaying disease progression.

Detection of aberration in human behavior using shallow neural network over smartphone inertial sensors data

AbstractThe integration of different Mobile Edge Computing (MEC) applications has significantly enhanced the realm of security and surveillance, with Human Activity Recognition (HAR) standing out as a crucial application. The diverse sensors found in smartphones have made it convenient for monitoring applications to gather and analyze data, rendering them valuable for HAR purposes. Moreover, MEC can be employed to automate surveillance, allowing intelligent monitoring of restricted areas to identify and respond to unwanted or suspicious activities. This research develops a system using motion sensors in smartphones to identify unusual human activities. People's smartphones were employed to monitor both suspicious and regular activities. Information was collected for various actions categorized as either suspicious or regular. When a person performs a certain action, the smartphone records a series of sensory data, analyse important patterns from the basic data, and then determines what the person is doing by combining information from different sensors. To prepare the data, information from different sensors was aligned to a shared timeline. In this study, we used a sliding window approach on synchronized data to feed sequences into LSTM and CNN models. These models, which include initial layers of LSTM and CNN, automatically find important patterns in the order of human activities. We combined SVM with the features extracted by the shallow Neural Network to make a mixed model that predicts suspicious activities. Lastly, we compared LSTM, CNN, and our new shallow mixed neural network using a new real‐time dataset. The mixed model of CNN and SVM achieved an accuracy of 94.43%. Additionally, the sliding window method's effectiveness was confirmed with a 4.28% improvement in accuracy.

Classification of Unisba Students' Graduation Time using Support Vector Machine Optimized with Grid Search Algorithm

Support Vector Machine is a classification method that finds the optimal hyperplane to separate two data classes. SVM has much better generalization performance than other methods. However, SVM needs to improve in determining hyperparameter values. Therefore, parameter optimization is necessary to determine the optimal hyperparameter value. Grid search is one of the parameter optimization methods that can improve the quality of SVM models. This study aims to assess the level of accuracy in predicting student graduation times by using five features that affect it. This study shows that the resulting SVM model optimized with the Grid Search Algorithm is quite consistent and prevents overfitting. By utilizing the results of SVM modelling, UNISBA is expected to improve the quality of graduates. The risk of delays in graduation can be considered early by paying attention to the background and achievements of students

Pollutants-mediated viral hepatitis in different types: assessment of different algorithms and time series models

The escalating frequency of environmental pollution incidents has raised significant concerns regarding the potential health impacts of pollutant fluctuations. Consequently, a comprehensive study on the role of pollutants in the prevalence of viral hepatitis is indispensable for the advancement of innovative prevention strategies. Monthly incidence rates of viral hepatitis from 2005 to 2020 were sourced from the Chinese Center for Disease Control and Prevention Infectious Disease Surveillance Information System. Pollution data spanning 2014–2020 were obtained from the National Oceanic and Atmospheric Administration (NOAA), encompassing pollutants such as CO, NO2, and O3. Time series analysis models, including seasonal auto-regressive integrated moving average (SARIMA), Holt-Winters model, and Generalized Additive Model (GAM), were employed to explore prediction and synergistic effects related to viral hepatitis. Spearman correlation analysis was utilized to identify pollutants suitable for inclusion in these models. Concurrently, machine learning (ML) algorithms were leveraged to refine the prediction of environmental pollutant levels. Finally, a weighted quantile sum (WQS) regression framework was developed to evaluate the singular and combined impacts of pollutants on viral hepatitis cases across different demographics, age groups, and environmental strata. The incidence of viral hepatitis in Beijing exhibited a declining trend, primarily characterized by HBV and HCV types. In predicting hepatitis prevalence trends, the Holt-Winters additive seasonal model outperformed the SARIMA multiplicative model ((1,1,0) (2,1,0) [12]). In the prediction of environmental pollutants, the SVM model demonstrated superior performance over the GPR model, particularly with Polynomial and Besseldot kernel functions. The combined pollutant risk effect on viral hepatitis was quantified as βWQS (95% CI) = 0.066 (0.018, 0.114). Among different groups, PM2.5 emerged as the most sensitive risk factor, notably impacting patients with HCV and HEV, as well as individuals aged 35–64. CO predominantly affected HAV patients, showing a risk effect of βWQS (95% CI) = − 0.0355 (− 0.0695, − 0.0016). Lower levels of PM2.5 and PM10 were associated with heightened risk of viral hepatitis incidence with a lag of five months, whereas elevated levels of PM2.5 (100–120 μg/m3) and CO correlated with increased hepatitis incidence risk with a lag of six months. The Holt-Winters model outperformed the SARIMA model in predicting the incidence of viral hepatitis. Among machine learning algorithms, SVM and GPR models demonstrated superior performance for analyzing pollutant data. Patients infected with HAV and HEV were primarily influenced by PM10 and CO, whereas SO2 and PM2.5 significantly impacted others. Individuals aged 35–64 years appeared particularly susceptible to these pollutants. Mixed pollutant exposures were found to affect the development of viral hepatitis with a notable lag of 5–6 months. These findings underscore the importance of long-term monitoring of pollutants in relation to viral hepatitis incidence.

Investigating the Relationship between Balanced Composition and Aesthetic Judgment through Computational Aesthetics and Neuroaesthetic Approaches

Background: Symmetry is a special kind of balance. This study aims to systematically explore and apply the role of balanced composition in aesthetic judgments by focusing on balanced composition features and employing research methods from computational aesthetics and neuroaesthetics. Methods: First, experimental materials were classified by quantifying balanced composition using several indices, including symmetry, center of gravity, and negative space. An EEG experiment was conducted with 18 participants, who were asked to respond dichotomously to the same stimuli under different judgment tasks (balance and aesthetics), with both behavioral and EEG data being recorded and analyzed. Subsequently, participants’ data were combined with balanced composition indices to construct and analyze various SVM classification models. Results: Participants largely used balanced composition as a criterion for aesthetic evaluation. ERP data indicated that from 300–500 ms post-stimulus, brain activation was more significant in the aesthetic task, with unbeautiful and imbalanced stimuli eliciting larger frontal negative waves and occipital positive waves. From 600–1000 ms, beautiful stimuli caused smaller negative waves in the PZ channel. The results of the SVM models indicated that the model incorporating aesthetic subject data (ACC = 0.9989) outperforms the model using only balanced composition parameters of the aesthetic object (ACC = 0.7074). Conclusions: Balanced composition is a crucial indicator in aesthetics, with similar early processing stages in both balance and aesthetic judgments. Multi-modal data models validated the advantage of including human factors in aesthetic evaluation systems. This interdisciplinary approach not only enhances our understanding of the cognitive and emotional processes involved in aesthetic judgments but also enables the construction of more reasonable machine learning models to simulate and predict human aesthetic preferences.

Consensus molecular subtyping of metastatic colorectal cancer expands biomarker-directed therapeutic benefit for patients with CMS1 and CMS2 tumors.

We developed a whole transcriptome sequencing (WTS)-based Consensus Molecular Subtypes (CMS) classifier using FFPE tissue and investigated its prognostic and predictive utility in a large clinico-genomic database of CRC patients (n = 24,939). The classifier was trained against the original CMS datasets using an SVM model and validated in an independent blinded TCGA dataset (88.0% accuracy). Kaplan-Meier estimates of overall survival (OS) and time-on-treatment (TOT) were calculated for each CMS (p < 0.05 considered significant). CMS2 tumors were enriched on left-side of colon and conferred the longest median OS. In RAS-wildtype mCRC, left-sided tumors and CMS2 classification were associated with longer TOT with anti-EGFR antibodies (cetuximab and panitumumab). When restricting to only CMS2, there was no significant difference in TOT between right- versus left-sided tumors. CMS1 tumors were associated with a longer median TOT with pembrolizumab relative to other CMS groups, even when analyzing only microsatellite stable (MSS) tumors. A WTS-based CMS classifier allowed investigation of a large multi-institutional clinico-genomic mCRC cohort, suggesting anti-EGFR therapy benefit for right-sided RAS-WT CMS2 tumors and immune checkpoint inhibitor benefit for MSS CMS1. Routine CMS classification of CRC provides important treatment associations that should be further investigated.

基于高光谱和人工智能模型的白茶鲜叶农药残留检测

The detection of pesticide residues in white tea fresh leaves is an important step to ensure the quality safety of white tea finished products. Traditional detection methods are costly and inefficient to realize the demand for fast, low-cost, and accurate detection of pesticide residues in white tea fresh leaves. In this study, five types of white tea fresh leaf pesticide residue sample data were obtained using hyperspectral imaging technology for the high-frequency detected pesticides Glyphosate and Bifenthrin, and the SVM and 1D-CNN models were established to detect the samples after noise reduction processing and feature band screening methods. The study shows that the 1D-CNN model has better feature extraction ability, in which the SG-CARS-1D-CNN model has the highest detection accuracy, which is 94.62%, 95.12%, 94.35%, 94.95%, and 95.27% for the five type of species samples, respectively. This study provides pesticide residue detection for white tea fresh leaves based on the combination of hyperspectral data and an artificial intelligence model, which provides an intelligent, nondestructive, efficient, and high-precision pesticide residue detection model for white tea fresh leaves.

Generating in-store customer journeys from scratch with GPT architectures

We propose a method that can generate customer trajectories and purchasing behaviors in retail stores simultaneously using Transformer-based deep learning structure. Utilizing customer trajectory data, layout diagrams, and retail scanner data obtained from a retail store, we trained a GPT-2 architecture from scratch to generate indoor trajectories and purchase actions. Additionally, we explored the effectiveness of fine-tuning the pre-trained model with data from another store. Results demonstrate that our method reproduces in-store trajectories and purchase behaviors more accurately than LSTM and SVM models, with fine-tuning significantly reducing the required training data.Graphic abstract