Landslide susceptibility mapping of mountain roads based on machine learning combined model

Landslide susceptibility mapping of mountain roads is frequently confronted by insufficient historical landslide sample data,multicollinearity of existing evaluation index factors,and inconsistency of evaluation factors due to regional environmental variations.Then,a single machine learning model can easily become overfitting,thus reducing the accuracy and robustness of the evaluation model.This paper proposes a combined machine-learning model to address the issues.The landslide susceptibility in mountain roads were mapped by using factor analysis to normalize and reduce the dimensionality of the initial condition factor and generating six new combination factors as evaluation indexes.The mountain roads in the Youxi County,Fujian Province,China were used for the landslide susceptibility mapping.Three most frequently used machine learning techniques,support vector machine(SVM),random forest(RF),and artificial neural network(ANN)models,were used to model the landslide susceptibility of the study area and validate the accuracy of this evaluation index system.The global minimum variance portfolio was utilized to construct a machine learning combined model.5-fold cross-validation,statistical indexes,and AUC(Area Under Curve)values were implemented to evaluate the predictive accuracy of the landslide susceptibility model.The mean AUC values for the SVM,RF,and ANN models in the training stage were 89.2%,88.5%,and 87.9%,respectively,and 78.0%,73.7%,and 76.7%,respectively,in the validating stage.In the training and validation stages,the mean AUC values of the combined model were 92.4% and 87.1%,respectively.The combined model provides greater prediction accuracy and model robustness than one single model.

Universal machine learning potential accelerates atomistic modeling of materials

With the rapid development of computer techniques,atomistic modeling is playing an increasingly important role in understanding the structure-activity relationship of materials.Molecular dynamics (MD) is a computational simulation approach to predicting the structural evolution of an atomic system over time,widely used to understand physical and chemical phenomena including phase transition,diffusion,crystallization,and reaction [1].

Framework for a Computer-Aided Treatment Prediction (CATP) System for Breast Cancer

This study offers a framework for a breast cancer computer-aided treat-ment prediction(CATP)system.The rising death rate among women due to breast cancer is a worldwide health concern that can only be addressed by early diagno-sis and frequent screening.Mammography has been the most utilized breast ima-ging technique to date.Radiologists have begun to use computer-aided detection and diagnosis(CAD)systems to improve the accuracy of breast cancer diagnosis by minimizing human errors.Despite the progress of artificial intelligence(AI)in the medical field,this study indicates that systems that can anticipate a treatment plan once a patient has been diagnosed with cancer are few and not widely used.Having such a system will assist clinicians in determining the optimal treatment plan and avoid exposing a patient to unnecessary hazardous treatment that wastes a significant amount of money.To develop the prediction model,data from 336,525 patients from the SEER dataset were split into training(80%),and testing(20%)sets.Decision Trees,Random Forest,XGBoost,and CatBoost are utilized with feature importance to build the treatment prediction model.The best overall Area Under the Curve(AUC)achieved was 0.91 using Random Forest on the SEER dataset.

A Novel Deep Learning Representation for Industrial Control System Data

Feature extraction plays an important role in constructing artificial intel-ligence(AI)models of industrial control systems(ICSs).Three challenges in this field are learning effective representation from high-dimensional features,data heterogeneity,and data noise due to the diversity of data dimensions,formats and noise of sensors,controllers and actuators.Hence,a novel unsupervised learn-ing autoencoder model is proposed for ICS data in this paper.Although traditional methods only capture the linear correlations of ICS features,our deep industrial representation learning model(DIRL)based on a convolutional neural network can mine high-order features,thus solving the problem of high-dimensional and heterogeneous ICS data.In addition,an unsupervised denoising autoencoder is introduced for noisy ICS data in DIRL.Training the denoising autoencoder allows the model to better mitigate the sensor noise problem.In this way,the represen-tative features learned by DIRL could help to evaluate the safety state of ICSs more effectively.We tested our model with absolute and relative accuracy experi-ments on two large-scale ICS datasets.Compared with other popular methods,DIRL showed advantages in four common indicators of AI algorithms:accuracy,precision,recall,and F1-score.This study contributes to the effective analysis of large-scale ICS data,which promotes the stable operation of ICSs.

A Hybrid Approach of TLBO and EBPNN for Crop YieldPrediction Using Spatial Feature Vectors

The prediction of crop yield is one of the important factor and also challenging,to predict the future crop yield based on various criteria’s.Many advanced technologies are incorporated in the agricultural processes,which enhances the crop yield production efficiency.The process of predicting the crop yield can be done by taking agriculture data,which helps to analyze and make important decisions before and during cultivation.This paper focuses on the prediction of crop yield,where two models of machine learning are developed for this work.One is Modified Convolutional Neural Network(MCNN),and the other model is TLBO(Teacher Learning Based Optimization)-a Genetic algorithm which reduces the input size of data.In this work,some spatial information used for analysis is the Normalized Difference Vegetation Index,Standard Precipitation Index and Vegetation Condition Index.TLBO finds some best feature value set in the data that represents the specific yield of the crop.So,these selected feature valued set is passed in the Error Back Propagation Neural Network for learning.Here,the training was done in such a way that all set of features were utilized in pair with their yield value as output.For increasing the reliability of the work whole experiment was done on a real dataset from Madhya Pradesh region of country India.The result shows that the proposed model has overcome various evaluation parameters on different scales as compared to previous approaches adopted by researchers.

Convolutional neural network for breast cancer diagnosis using diffuse optical tomography

We have developed a computer-aided diagnosis system based on a convolutional neural network that aims to classify breast mass lesions in optical tomographic images obtained using a diffuse optical tomography system,which is suitable for repeated measurements in mass screening.Sixty-three optical tomographic images were collected from women with dense breasts,and a dataset of 12602D gray scale images sliced from these 3D images was built.After image preprocessing and normalization,we tested the network on this dataset and obtained 0.80 specificity,0.95 sensitivity,90.2%accuracy,and 0.94 area under the receiver operating characteristic curve(AUC).Furthermore,a data augmentation method was implemented to alleviate the imbalance between benign and malignant samples in the dataset.The sensitivity,specificity,accuracy,and AUC of the classification on the augmented dataset were 0.88,0.96,93.3%,and 0.95,respectively.

Transcriptomic and machine learning analyses identify hub genes of metabolism and host immune response that are associated with the progression of breast capsular contracture

Capsular contracture is a prevalent and severe complication that affects the post-operative outcomes of patients who receive silicone breast implants.At present,prosthesis replacement is the major treatment for capsular contracture after both breast augmentation procedures and breast reconstruction following breast cancer surgery.However,the mecha-nism(s)underlying breast capsular contracture remains unclear.This study aimed to identify the biological features of breast capsular contracture and reveal the potential underlying mechanism using RNA sequencing.Sample tissues from 12 female patients(15 breast capsules)were divided into low capsular contracture(LCC)and high capsular contracture(HCC)groups based on the Baker grades.Subsequently,41 lipid metabolism-related genes were identified through enrichment analysis,and three of these genes were identified as candidate genes by SVM-RFE and LASSO algorithms.We then compared the proportions of the 22 types of im-mune cells between the LCC and HCC groups using a CIBERSORT analysis and explored the Cor-relation between the candidate hub features and immune cells.Notably,PRKAR2B was positively correlated with the differentially clustered immune cells,which were M1 macro-phages and follicular helper T cells(area under the ROC=0.786).In addition,the expression of PRKAR2B at the mRNA or protein level was lower in the HCC group than in the LCC group.Potential molecular mechanisms were identified based on the expression levels in the high and low PRKAR2B groups.Our findings indicate that PRKAR2B is a novel diagnostic biomarker for breast capsular contracture and might also influence the grade and progression of capsularcontracture.

A Review of Machine Learning and Algorithmic Methods for Protein Phosphorylation Site Prediction

Post-translational modifications(PTMs)have key roles in extending the functional diversity of proteins and,as a result,regulating diverse cellular processes in prokaryotic and eukaryotic organisms.Phosphorylation modification is a vital PTM that occurs in most proteins and plays a significant role in many biological processes.Disorders in the phosphorylation process lead to multiple diseases,including neurological disorders and cancers.The purpose of this review is to organize this body of knowledge associated with phosphorylation site(p-site)prediction to facilitate future research in this field.At first,we comprehensively review all related databases and introduce all steps regarding dataset creation,data preprocessing,and method evaluation in p-site prediction.Next,we investigate p-site prediction methods,which are divided into two computational groups:algorithmic and machine learning(ML).Additionally,it is shown that there are basically two main approaches for p-site prediction by ML:conventional and end-to-end deep learning methods,both of which are given an overview.Moreover,this review introduces the most important feature extraction techniques,which have mostly been used in p-site prediction.Finally,we create three test sets from new proteins related to the released version of the database of protein post-translational modifications(dbPTM)in 2022 based on general and human species.Evaluating online p-site prediction tools on newly added proteins introduced in the dbPTM 2022 release,distinct from those in the dbPTM 2019 release,reveals their limitations.In other words,the actual performance of these online p-site prediction tools on unseen proteins is notably lower than the results reported in their respective research pape.

Software design pattern mining using classification-based techniques

Design patterns are often used in the development of object-oriented software. It offers reusable abstract information that is helpful in solving recurring design problems. Detecting design patterns is beneficial to the comprehension and maintenance of object-oriented software systems. Several pattern detection techniques based on static analysis often encounter problems when detecting design patterns for identical structures of patterns. In this study, we attempt to detect software design patterns by using software metrics and classification-based techniques. Our study is conducted in two phases： creation of metrics-oriented dataset and detection of software design patterns. The datasets are prepared by using software metrics for the learning of classifiers. Then, pattern detection is performed by using classification-based techniques. To evaluate the proposed method, experiments are conducted using three open source software programs, JHotDraw, QuickUML, and JUnit, and the results are analyzed.

Single stain hyperspectral imaging for accurate fungal pathogens identification and quantification

The most widely used method of identification of microbial morphology and structure is microscopy,but it can be difficult to distinguish between pathogens with a similar appearance.Existing fluorescent staining methods require a combination of a variety of fluorescent materials to meet this demand.In this study,unique concentration-dependent fluorescent carbon dots(CDs)were synthesized for the identification and quantification of pathogens.The emission wavelength of the CDs could be tuned spanning the full visible region by virtue of aggregation-induced narrowing of bandgaps.This tunable emission wavelength of the specific concentration response to diverse microbes can be used to distinguish microorganisms with a similar appearance,even in a same genus.A hyperspectral microscopy system was demonstrated to distinguish Aspergillus flavus and A.fumigatus based on the results above.The identification accuracy of the two similar-looking pathogens can be close to 100%,and the relative proportions and spatial distributions can also be profiled from the mixture of the pathogens.This technique can provide a solution to the fast detection of microorganisms and is potentially applicable to a wide range of problems in areas such as healthcare,food preparation,biotechnology,and health emergency.

Automatic sub-pixel co-registration of Landsat-8 Operational Land Imager and Sentinel-2A Multi-Spectral Instrument images using phase correlation and machine learning based mapping

This study investigates misregistration issues between Landsat-8/Operational Land Imager and Sentinel-2A/Multi-Spectral Instrument at 30 m resolution,and between multi-temporal Sentinel-2A images at 10 m resolution using a phase-correlation approach and multiple transformation functions.Co-registration of 45 Landsat-8 to Sentinel-2A pairs and 37 Sentinel-2A to Sentinel-2A pairs were analyzed.Phase correlation proved to be a robust approach that allowed us to identify hundreds and thousands of control points on images acquired more than 100 days apart.Overall,misregistration of up to 1.6 pixels at 30 m resolution between Landsat-8 and Sentinel-2A images,and 1.2 pixels and 2.8 pixels at 10 m resolution between multi-temporal Sentinel-2A images from the same and different orbits,respectively,were observed.The non-linear random forest regression used for constructing the mapping function showed best results in terms of root mean square error(RMSE),yielding an average RMSE error of 0.07±0.02 pixels at 30 m resolution,and 0.09±0.05 and 0.15±0.06 pixels at 10 m resolution for the same and adjacent Sentinel-2A orbits,respectively,for multiple tiles and multiple conditions.A simpler 1st order polynomial function(affine transformation)yielded RMSE of 0.08±0.02 pixels at 30 m resolution and 0.12±0.06(same Sentinel-2A orbits)and 0.20±0.09(adjacent orbits)pixels at 10 m resolution.

Unsupervised Dynamic Fuzzy Cognitive Map

Fuzzy Cognitive Map （FCM） is an inference network, which uses cyclic digraphs for knowledge representation and reasoning. Along with the extensive applications of FCMs, there are some limitations that emerge due to the deficiencies associated with FCM itself. In order to eliminate these deficiencies, we propose an unsupervised dynamic fuzzy cognitive map using behaviors and nonlinear relationships. In this model, we introduce dynamic weights and trend-effects to make the model more reasonable. Data credibility is also considered while establishing a machine learning model. Subsequently, we develop an optimized Estimation of Distribution Algorithm （EDA） for weight learning. Experimental results show the practicability of the dynamic FCM model. In comparison to the other existing algorithms, the proposed algorithm has better performance in terms of convergence and stability.