Linear SVM Model Research Articles

Acoustic absorption characterization and modeling using support vector regression of plasterboards reinforced with woven Moroccan sisal fiber

The acoustic comfort and environmental concerns in the building sector are two interconnected and crucial aspects for the sustainable development of the construction industry. This study investigates the acoustic absorption properties of plasterboards reinforced with woven fabric made from Moroccan sisal fiber. Three different weave designs, Basket 2-2, 2/2 Twill, and 4-Harness Satin, were produced using a conventional weaving process. Plasterboards were manually fabricated by varying the number of fabric layers (one, two, or three) and employing a water/plaster ratio of 0.7. The acoustic performance of the plasterboards was evaluated using an impedance tube according to ISO 10534-2. The results demonstrated that the plasterboards reinforced with the Basket 2-2 weave achieved the highest sound absorption coefficient, reaching 0.39 at 1700 Hz with three layers, significantly higher than pure plasterboards, which exhibited a maximum coefficient of 0.05. The study also employed support vector regression (SVR) models to predict the sound absorption coefficient, with the linear SVM model achieving the best predictive accuracy (R² = 0.88, RMSE = 0.024). These findings underscore the potential of Moroccan sisal fiber as an eco-friendly reinforcement for improving the acoustic absorption of plasterboards.

Analysis of Factors Causing Urban Road Traffic Accidents Based on XGboost Algorithm

To further strengthen road traffic safety management and improve the accuracy of early warning systems for road traffic safety, a model for factors causing urban road traffic accidents based on the XGBoost algorithm is proposed. Firstly, SMOTE is used to process the unbalanced data, including supplementing the missing values, deleting the duplicate values, and visualizing the data. Then the prediction model is built by the XGBoost algorithm. By comparing and analyzing the results with the LR model, linear SVM model, DT model and Lightgbm model, the average accuracy rate of the XGBoost model reaches 0.979. Based on the XGBoost algorithm, the analysis of the factors causing urban road traffic accidents has better prediction performance, which can provide a reliable reference for preventing traffic accidents.

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.

Efficacy and biomarker analysis of carboplatin plus taxanes neoadjuvant chemotherapy in triple-negative breast cancer: A prospective multicenter cohort study.

e12619 Background: The efficacy and survival data of carboplatin plus taxane (anthracycline-free) neoadjuvant chemotherapy (NAC) in triple-negative breast cancer (TNBC) was lack of a large-sample study. The predictive biomarker of efficacy based on cell-free DNA (cfDNA) whole-methylome sequencing (WMS) has not been reported yet. Methods: The prospective multi-center cohort study was conducted in four hospitals of Chinabetween 2016 and 2023. Stage II-III TNBC patients were enrolled to receive NAC of carboplatin (AUC 5) every 3 weeks or carboplatin (AUC 4) every 2 weeks plus taxane(standard dose) for 4-6 cycles. Primary study endpoint were pathological complete response (pCR) and relapse-free survival (RFS). Plasma samples were prospectively collected at baseline (T1) and after NAC(T2). Chromosomal aneuploidy of featured fragments (CAFF),fragment size index (FSI) and methylation density score (MD) of cfDNA were detected with WMS. Results: A total of 267 patients were included in the study. The median age was 49 years, 156 patients (58.4%) were stage III disease. 147 patients (55.1%) received the triweekly NAC. 263 patients underwent breast surgery after NAC and 106 patients (40.3%) achieved pCR. The pCR were similar in biweekly or triweekly groups (39.8% vs 40.7%, P=0.89). The 3-year RFS and overall survival (OS) were 77.9%, 87.6%, respectively. Patients who achieved pCR had a significant better RFS (95.5%) and OS (97.7%) than those non-pCR (76.6%, P<0.001; 81.2%, P<0.001). A total of 66 patients with 120 plasma samples (64 samples at T1, 56 samples at T2) were included in WMS analysis. Patients with CAFF, FSI or MD positive at T1 had a higher tumor burden (stage III or cN2-3, all P values <0.05). The proportion of patients with FSI negative at T2 was significantly higher in pCR group compared to non-pCR(86.2% vs 59.3%, P=0.034). There is a similar tendency in patients with CAFF negative. Patients with MD positive at T1 was significantly associated with poor RFS compared to MD negative (HR = 7.36, 95% CI: 0.93-58.75, Log-rank P=0.028). A linear SVM model based on FSI, CAFF, combining with immune cell (effector memory CD8 T cells, immature B cells) and clinical features was developed to predict pCR, with AUC = 0.90 for training dataset and AUC = 0.86 for testing data. Conclusions: Our large-sample study further confirmed that carboplatin plus taxanes (anthracycline-free) NAC in TNBC is an effective option with clinical applicability. Biomarkers based on cfDNA WMS may offer some predictive and prognostic value which needed to be further investigated.

Securing SDN Networks: Employing LSTM and Linear SVM Models for Enhanced Network Security with VPN Integration

Securing SDN Networks: Employing LSTM and Linear SVM Models for Enhanced Network Security with VPN Integration

Research on the Prediction of Boston House Price Based on Linear Regression, Random Rorest, Xgboost and SVM Models

Regression problems, which make up a significant portion of machine learning research, include the Boston housing price forecast problem. Regression problems are a subset of artificial intelligence. Regression problem-solving algorithms that are more frequently used four different machine learning models—the linear regression model, the Random Forest model based on an integrated learning technique, the XGBoost model, and the SVM model—are utilized for training and testing in this study. These models were chosen based on the real-world Boston house price prediction problem. From various angles, the effectiveness of the various algorithmic models on the regression problem of house price prediction was evaluated, and it was determined that among the many algorithmic models. For this problem, the best model is XGBoost Regression and the worst model was the SVM model. The most typical benefit of the XGBoost model is that It can capture complex non-linear relationships between variables.The disadvantage of the SVM model is its computational complexity.

Geo-additive mixed model with variable selection using the adaptive elastic net to handle nonresponse in official rice productivity survey

This study is motivated by the nonresponse problem in the official rice productivity survey conducted by Statistics Indonesia. Handling nonresponse is essential to support the vision as a quality statistical data provider for advanced Indonesia. This study aimed to improve the quality of official rice productivity data by imputing nonresponse data using the geo-additive mixed model with variable selection. Then we simulated three nonresponse data scenarios to determine whether the imputation technique is better than the listwise deletion. The results showed that the proposed imputation model was the best-imputed model for estimating rice productivity compared to the linear regression, SVM, and geo-additive mixed models without variable selection. The proposed model outperforms other models when the data conditions experience spatial autocorrelation and multicollinearity. The proposed model had two advantages. First, variable selection using the adaptive elastic net could overcome multicollinearity problems. Second, adding the mixed geo-additive function caused the model’s residuals to have no spatial autocorrelation. We showed by simulation using empirical data that the proposed imputation method reduces bias when the nonresponse data is not random. Our methodology presents a valuable alternative for improving the quality of official statistics.

Detection of IoT Botnet Cyber Attacks using Machine Learning

Since they were first used, systems have faced threats from viruses, worms, and hacking attacks. In 2018, there were more devices online than there were people, and this tendency will continue to grow, with an estimated 80 billion devices online by 2024. It is difficult to secure this equipment and the data that flows between them since IoT botnet attacks (IBA) are becoming more and more common. Potential hackers for data theft and cyberattacks have been enticed by the overwhelming quantity and omnipresent presence. One of the biggest issues with the Internet of Things is security. The main goal of this research project is to develop a workable machine learning algorithm-based model to identify and counteract botnet-based attacks on IoT networks. The suggested model addresses the security concern of the dangers provided by bots. The BoT-IoT dataset was used to train a variety of machine learning techniques, including linear regression, logistic regression, K-Nearest Neighbor (KNN), and SVM models. The performance of the system’s results in an F-measure of: 1) 98.0%, 2) 99.0%, and 3) 99.0%. 4) 99.0%. This demonstrates that the proposed models can automatically separate between network activities is malicious or normal.

Safemedchain — drug counterfeit prevention and recommendation using blockchain and machine learning

Counterfeit drugs are without a doubt becoming a greater hazard to consumers and the pharmaceutical sector. As a result, real-time visibility of drug manufacturing and management is required. The proposed system uses Ethereum blockchain as the main technology. The primary advantage of blockchain technology is that the transactions are maintained in immutable digital ledger format and it may be read easily without jeopardizing the users’ security and privacy. In our proposed system, the admin validates and adds the manufacturers. The manufacturer after registering and logging in can perform tasks like adding the drug and seller list. The seller can place order to the manufacturer which the manufacturer can accept or reject. The seller can update status of order of accepted orders to delivered. The customer can view the order details by entering the serial number on the drug package. Any transaction or exchange that occurs in the network is recorded in the chain. It functions similarly to other networks, but blockchain technology is distinguished by the fact that no data can be removed or altered by anyone in the network. No changes to the network can be made unless it has been validated by all of the network’s authorized users. All the information stored can be read by anybody so to incorporate more security, AES has been used to store data in the blockchain. The use of AES encryption technique distinguishes this system from all the existing implementations. Thus, this makes it easy to trace to the exact point in the supply chain and detect any counterfeit drugs in movement. As an extension to the drug counterfeit prevention system a Drug Recommendation System is also performed using the ensemble model with a combination of Random Forest and Logistic Regression for sentiment analysis training. Furthermore, when compared to the existing Linear SVM model, which has an accuracy of 90.39%, the suggested model has the best accuracy of 93.31%. Using the obtained sentiment for each drug, the drug is predicted accurately for the specified medical condition.

A Machine Learning Technique for Rice Blast Disease Severity Prediction Using K-Means SMOTE Class Balancing

Rice blast disease is strongly dependent on environmental and climate factors. This paper demonstrates the integration of a rice blast disease severity prediction model based on climate factors, providing a decision-support framework for farmers to overcome these problems. The major contribution of the proposed study is to predict the severity of rice blast disease using the linear SVM model. Prediction of rice blast disease severity is divided into four classes: 0, 1, 2, and 3. Data imbalance is the most challenging problem in multi-class classification. This study has efficiently handled imbalanced data using k-means SMOTE and SMOTE oversampling techniques to balance training and testing data. Finally, cross-location and cross-year models are developed using a linear support vector machine and predict the severity of rice blast disease to the classes 0, 1, 2, 3, respectively. Cross-year and cross-location models are cross-validated using five-fold cross-validation.

Machine Learning-Based Genome-Wide Salivary DNA Methylation Analysis for Identification of Noninvasive Biomarkers in Oral Cancer Diagnosis.

Simple SummaryBecause tissue biopsy is the gold standard for diagnosing oral cancer, it is often performed to confirm disease during screening, management, and monitoring. However, many reports are negative. Salivary biomarkers can provide the preliminary stratification of suspicious lesions to encourage patient selection in clinical practice. However, the discovery and implementation of salivary biomarkers still need to be refined. Therefore, in this study, we successfully utilized machine learning techniques to select optimal methylome biomarkers that may be applied for oral cancer diagnoses.This study aims to examine the feasibility of ML-assisted salivary-liquid-biopsy platforms using genome-wide methylation analysis at the base-pair and regional resolution for delineating oral squamous cell carcinoma (OSCC) and oral potentially malignant disorders (OPMDs). A nested cohort of patients with OSCC and OPMDs was randomly selected from among patients with oral mucosal diseases. Saliva samples were collected, and DNA extracted from cell pellets was processed for reduced-representation bisulfite sequencing. Reads with a minimum of 10× coverage were used to identify differentially methylated CpG sites (DMCs) and 100 bp regions (DMRs). The performance of eight ML models and three feature-selection methods (ANOVA, MRMR, and LASSO) were then compared to determine the optimal biomarker models based on DMCs and DMRs. A total of 1745 DMCs and 105 DMRs were identified for detecting OSCC. The proportion of hypomethylated and hypermethylated DMCs was similar (51% vs. 49%), while most DMRs were hypermethylated (62.9%). Furthermore, more DMRs than DMCs were annotated to promoter regions (36% vs. 16%) and more DMCs than DMRs were annotated to intergenic regions (50% vs. 36%). Of all the ML models compared, the linear SVM model based on 11 optimal DMRs selected by LASSO had a perfect AUC, recall, specificity, and calibration (1.00) for OSCC detection. Overall, genome-wide DNA methylation techniques can be applied directly to saliva samples for biomarker discovery and ML-based platforms may be useful in stratifying OSCC during disease screening and monitoring.

The alterations of brain functional connectivity networks in major depressive disorder detected by machine learning through multisite rs-fMRI data

BackgroundThe current diagnosis of major depressive disorder (MDD) is mainly based on the patient's self-report and clinical symptoms. Machine learning methods are used to identify MDD using resting-state functional magnetic resonance imaging (rs-fMRI) data. However, due to large site differences in multisite rs-fMRI data and the difficulty of sample collection, most of the current machine learning studies use small sample sizes of rs-fMRI datasets to detect the alterations of functional connectivity (FC) or network attribute (NA), which may affect the reliability of the experimental results. MethodsMultisite rs-fMRI data were used to increase the size of the sample, and then we extracted the functional connectivity (FC) and network attribute (NA) features from 1611 rs-fMRI data (832 patients with MDD (MDDs) and 779 healthy controls (HCs)). ComBat algorithm was used to harmonize the data variances caused by the multisite effect, and multivariate linear regression was used to remove age and sex covariates. Two-sample t-test and wrapper-based feature selection methods (support vector machine recursive feature elimination with cross-validation (SVM-RFECV) and LightGBM's "feature_importances_" function) were used to select important features. The Shapley additive explanations (SHAP) method was used to assign the contribution of features to the best classification effect model. ResultsThe best result was obtained from the LinearSVM model trained with the 136 important features selected by SVMRFE-CV. In the nested five-fold cross-validation (consisting of an outer and an inner loop of five-fold cross-validation) of 1611 data, the model achieved the accuracy, sensitivity, and specificity of 68.90 %, 71.75 %, and 65.84 %, respectively. The 136 important features were tested in a small dataset and obtained excellent classification results after balancing the ratio between patients with depression and HCs. ConclusionsThe combined use of FC and NA features is effective for classifying MDDs and HCs. The important FC and NA features extracted from the large sample dataset have some generalization performance and may be used as a reference for the altered brain functional connectivity networks in MDD.

Theme Identification using Machine Learning Techniques

With the abundance of online research platforms, much information presented in PDF files, such as articles and journals, can be obtained easily. In this case, students completing research projects would have many downloaded PDF articles on their laptops. However, identifying the target articles manually within the collection can be tiring as most articles consist of several pages that need to be analyzed. Reading each article to determine if the article relates theme and organizing the articles based on themes is time and energy-consuming. Referring to this problem, a PDF files organizer that implemented a theme identifier is necessary. Thus, work will focus on automatic text classification using the machine learning methods to build a theme identifier employed in the PDF files organizer to classify articles into augmented reality and machine learning. A total of 1000 text documents for both themes were used to build the classification model. Moreover, the pre-preprocessing step for data cleaning and TF-IDF feature extraction for text vectorization and to reduce sparse vectors were performed. 80% of the dataset were used for training, and the remaining were used to validate the trained models. The classification models proposed in this work are Linear SVM and Multinomial Naïve Bayes. The accuracy of the models was evaluated using a confusion matrix. For the Linear SVM model, grid-search optimization was performed to determine the optimal value of the Cost parameter.

Evaluating Performance of EEG Data-Driven Machine Learning for Traumatic Brain Injury Classification.

Objectives:Big data analytics can potentially benefit the assessment and management of complex neurological conditions by extracting information that is difficult to identify manually. In this study, we evaluated the performance of commonly used supervised machine learning algorithms in the classification of patients with traumatic brain injury (TBI) history from those with stroke history and/or normal EEG.Methods:Support vector machine (SVM) and K-nearest neighbors (KNN) models were generated with a diverse feature set from Temple EEG Corpus for both two-class classification of patients with TBI history from normal subjects and three-class classification of TBI, stroke and normal subjects.Results:For two-class classification, an accuracy of 0.94 was achieved in 10-fold cross validation (CV), and 0.76 in independent validation (IV). For three-class classification, 0.85 and 0.71 accuracy were reached in CV and IV respectively. Overall, linear discriminant analysis (LDA) feature selection and SVM models consistently performed well in both CV and IV and for both two-class and three-class classification. Compared to normal control, both TBI and stroke patients showed an overall reduction in coherence and relative PSD in delta frequency, and an increase in higher frequency (alpha, mu, beta and gamma) power. But stroke patients showed a greater degree of change and had additional global decrease in theta power.Conclusions:Our study suggests that EEG data-driven machine learning can be a useful tool for TBI classification.Significance:Our study provides preliminary evidence that EEG ML algorithm can potentially provide specificity to separate different neurological conditions.

The structural similarity index for IMRT quality assurance: radiomics‐based error classification

The implementation of radiomics and machine learning (ML) techniques on analyzing two-dimensional gamma maps has been demonstrated superior to the conventional gamma analysis for error identification in intensity modulated radiotherapy (IMRT) quality assurance (QA). Recently, the Structural SIMilarity (SSIM) sub-index maps were shown to be able to reveal the error types of the dose distributions. In this study, we aimed to apply radiomics analysis on SSIM sub-index maps and develop ML models to classify delivery errors in patient-specific dynamic IMRT QA. Twenty-one sliding-window IMRT plans of 180 beams for three treatment sites were involved in this study. Four types of machine-related errors of various magnitudes were simulated for each beam at each control point, including the monitor unit (MU) variations, same-directional and opposite-directional shifts of the multileaf collimators (MLCs) and random mispositioning of the MLCs. In the QA process, a total of 1620 portal dose (PD) images were acquired for the beams with and without errors. The predicted PD images of the original beams were set as references. To quantify the agreement between a measured PD image and the corresponding predicted PD image, four difference maps including three SSIM sub-index maps, and one dose difference-derived map were calculated. Then, radiomic features were extracted from the four difference maps of each measured PD image. We tested four typical classifiers including linear discriminant classifier (LDC), two supporting vector machine (SVM) classifiers, and random forest (RF) for this multiclass classification task. A nested cross-validation scheme was used for model evaluations, where the SVM recursive feature elimination method was applied for feature selection. Finally, the performance of the ML model on identifying the error-free and the erroneous cases was compared to that of the conventional gamma analysis. The statistics of the selected features showed that all of the difference maps and the feature categories made balanced contributions to solve this classification task. Best performance was achieved by the Linear-SVM model with average overall classification accuracy of 0.86. Specifically, the average classification accuracies of the shift, opening, and the random errors were around 0.9. Moreover, ~80% of error-free and MU errors were correctly classified. Using gamma analysis, the 3mm/3% criterion was found insensitive to errors (sensitivity was only 0.33). Although the sensitivity to errors with the 2mm/2% criterion increased to 0.79, still 8% worse than that of the ML model. We proposed an ML-based method for machine-related error identification in patient-specific dynamic IMRT QA, where radiomic analysis on SSIM sub-index maps were used for feature extraction. With extensive validation to select the best features and classifiers, high accuracies in error classification were achieved. Compared with the conventional gamma threshold method, this approach has great potential in error identification for the patient-specific IMRT QA process.

Rapid discrimination of intact beef, venison and lamb meat using Raman spectroscopy

With increasing demand for fast and reliable techniques for intact meat discrimination, we explore the potential of Raman spectroscopy in combination with three chemometric techniques to discriminate beef, lamb and venison meat samples. Ninety (90) intact red meat samples were measured using Raman spectroscopy, with the acquired spectral data preprocessed using a combination of rubber-band baseline correction, Savitzky-Golay smoothing and standard normal variate transformation. PLSDA and SVM classification were utilized in building classification models for the meat discrimination, whereas PCA was used for exploratory studies. Results obtained using linear and non-linear kernel SVM models yielded sensitivities of over 87 and 90 % respectively, with the corresponding specificities above 88 % on validation against a test set. The PLSDA model yielded over 80 % accuracy in classifying each of the meat specie. PLSDA and SVM classification models in combination with Raman spectroscopy posit an effective technique for red meat discrimination.

Prediction and Diagnosis of COVID-19 using Machine Learning Algorithms

The world is reworking in a digital era. However, the field of medicine was quite repulsive to technology. Recently, the advent of newer technologies like machine learning has catalyzed its adoption into healthcare. The blending of technology and medicine is facilitating a wealth of innovation that continues to improve lives. With the realm of possibility, machine learning is discovering various trends in a dataset and it is globally practiced in various medical conditions to predict the results, diagnose, analyze, treat, and recover. Machine Learning is aiding a lot to fight the battle against Covid-19. For instance, a face scanner that uses ML is used to detect whether a person has a fever or not. Similarly, the data from wearable technology like Apple Watch and Fitbit can be used to detect the changes in resting heart rate patterns which help in detecting coronavirus. According to a study by the Hindustan Times, the number of cases is rapidly increasing. Careful risk assessments should identify hotspots and clusters, and continued efforts should be made to further strengthen capacities to respond, especially at sub-national levels. The core public health measures for the Covid-19 response remain, rapidly detect, test, isolate, treat, and trace all contacts. The work presented in this paper represents the system that predicts the number of coronavirus cases in the upcoming days as well as the possibility of the infection in a particular person based on the symptoms. The work focuses on Linear Regression and SVM models for predicting the curve of active cases. SVM is least affected by noisy data, and it is not prone to overfitting. To diagnose a person our application has a certain question that needs to be answered. Based on this, the KNN model provides the maximum likelihood result of a person being infected or not. Tracking and monitoring in the course of such pandemic help us to be prepared.

Using VADER sentiment and SVM for predicting customer response sentiment

Customer support is important to corporate operations, which involves dealing with disgruntled customer and content customers that can have different requirements. As such, it is important to quickly extract the sentiment of support errands. In this study we investigate sentiment analysis in customer support for a large Swedish Telecom corporation. The data set consists of 168,010 e-mails divided into 69,900 conversation threads without any sentiment information available. Therefore, VADER sentiment is used together with a Swedish sentiment lexicon in order to provide initial labeling of the e-mails. The e-mail content and sentiment labels are then used to train two Support Vector Machine models in extracting/classifying the sentiment of e-mails. Further, the ability to predict sentiment of not-yet-seen e-mail responses is investigated. Experimental results show that the LinearSVM model was able to extract sentiment with a mean F1-score of 0.834 and mean AUC of 0.896. Moreover, the LinearSVM algorithm was also able to predict the sentiment of an e-mail one step ahead in the thread (based on the text in the an already sent e-mail) with a mean F1-score of 0.688 and the mean AUC of 0.805. The results indicate a predictable pattern in e-mail conversation that enables predicting the sentiment of a not-yet-seen e-mail. This can be used e.g. to prepare particular actions for customers that are likely to have a negative response. It can also provide feedback on possible sentiment reactions to customer support e-mails.

A Novel Ensemble Approach for Landslide Susceptibility Mapping (LSM) in Darjeeling and Kalimpong Districts, West Bengal, India

Landslides are among the most harmful natural hazards for human beings. This study aims to delineate landslide hazard zones in the Darjeeling and Kalimpong districts of West Bengal, India using a novel ensemble approach combining the weight-of-evidence (WofE) and support vector machine (SVM) techniques with remote sensing datasets and geographic information systems (GIS). The study area currently faces severe landslide problems, causing fatalities and losses of property. In the present study, the landslide inventory database was prepared using Google Earth imagery, and a field investigation carried out with a global positioning system (GPS). Of the 326 landslides in the inventory, 98 landslides (30%) were used for validation, and 228 landslides (70%) were used for modeling purposes. The landslide conditioning factors of elevation, rainfall, slope, aspect, geomorphology, geology, soil texture, land use/land cover (LULC), normalized differential vegetation index (NDVI), topographic wetness index (TWI), sediment transportation index (STI), stream power index (SPI), and seismic zone maps were used as independent variables in the modeling process. The weight-of-evidence and SVM techniques were ensembled and used to prepare landslide susceptibility maps (LSMs) with the help of remote sensing (RS) data and geographical information systems (GIS). The landslide susceptibility maps (LSMs) were then classified into four classes; namely, low, medium, high, and very high susceptibility to landslide occurrence, using the natural breaks classification methods in the GIS environment. The very high susceptibility zones produced by these ensemble models cover an area of 630 km2 (WofE& RBF-SVM), 474 km2 (WofE& Linear-SVM), 501km2 (WofE& Polynomial-SVM), and 498 km2 (WofE& Sigmoid-SVM), respectively, of a total area of 3914 km2. The results of our study were validated using the receiver operating characteristic (ROC) curve and quality sum (Qs) methods. The area under the curve (AUC) values of the ensemble WofE& RBF-SVM, WofE & Linear-SVM, WofE & Polynomial-SVM, and WofE & Sigmoid-SVM models are 87%, 90%, 88%, and 85%, respectively, which indicates they are very good models for identifying landslide hazard zones. As per the results of both validation methods, the WofE & Linear-SVM model is more accurate than the other ensemble models. The results obtained from this study using our new ensemble methods can provide proper and significant information to decision-makers and policy planners in the landslide-prone areas of these districts.

Regional Economic Activity Derived From MODIS Data: A Comparison With DMSP/OLS and NPP/VIIRS Nighttime Light Data

Defense Meteorological Satellite Program/Operational Linescan System (DMSP/OLS) and Suomi National Polar-Orbiting Partnership Visible Infrared Imaging Radiometer Suite (NPP/VIIRS) nighttime light data are the two most commonly used indicators of gross domestic product (GDP) estimation. Few studies explore the potential of daytime satellite data for estimating GDP. This study demonstrates a linear support vector machine (Linear-SVM) model to estimate GDP over Hubei province and Guangdong province, China, in 2013 from Moderate Resolution Imaging Spectroradiometer (MODIS) data. Also, a comparison of MODIS data with DMSP/OLS and NPP/VIIRS nighttime light data was conducted. Results show that the Linear-SVM model (Hubei: R 2 = 0.66, 0.71, 0.92; Guangdong: R 2 = 0.37, 0.32, 0.67) has better model performance than simple linear regression ( R 2 = 0.54, 0.59, 0.86; R 2 = 0.23, 0.23, 0.63) based on DMSP/OLS nighttime lights, DMSP/OLS corrected nighttime lights, and NPP/VIIRS nighttime lights, respectively, while MODIS data has model performance of R 2 = 0.77 (Hubei) and R 2 = 0.55 (Guangdong) based on the Linear-SVM model, further indicating that MODIS data improves the accuracy of GDP estimation compared to DMSP/OLS nighttime lights. In addition, MODIS data produced finer GDP estimation than DMSP/OLS nighttime lights, especially in dark and light saturated areas. Although MODIS data is not as accurate as the NPP/VIIRS nighttime lights for estimating GDP, the proposed method could be applicable to other daytime satellite data and has broad prospects for improving the spatial and temporal resolution of regional economic activity and improving estimation accuracy.