Search

A dual-stage model for classifying Parkinson's disease severity, through a detailed analysis of Gait signals using force sensors and machine learning approaches, is proposed in this study. Parkinson's disease is the primary neurodegenerative disorder that results in a gradual reduction in motor function. Early detection and monitoring of the disease progression is highly challenging due to the gradual progression of symptoms and the inadequacy of conventional methods in identifying subtle changes in mobility. The proposed dual-stage model utilized a hypertuned Random Forest Tree (RFT) to classify the subjects into PD and non-PD classes at Stage 1 and a hypertuned Ensemble Regressor (ER) to predict the severity of illness at Stage 2. Further, we have implemented the proposed model on the data signals gathered from both feet of 166 participants using Vertical Ground Reaction Force Sensors (VGRF). The dataset comprised 93 persons with Parkinson's disease and 73 healthy controls. The dataset (imbalance) collected from both feet is passed to the preprocessing phase (for balancing data using the SMOTE method), followed by the feature extraction phase to extract features related to time, frequency, spatial, and temporal features domains that are highly effective for detecting and assigning severity levels of PD. A Recursive Feature Elimination method is also used to select the optimal set of features to improve the model performance. It is acknowledged that the early detection of Parkinson's disease is contingent upon critical parameters, including stride length, stance duration, swing interval, double limb support, step time, and step length. The crucial evaluation metrics used for evaluating model performance include accuracy, mean absolute error, and root mean square error. The findings indicate that the suggested model significantly surpasses current methodologies. It attained an accuracy of 97.5 ± 2.1%, Sensitivity of 97% ± 2.5%, and average Specificity of 95% ± 2.2% in differentiating between PD and non-PD participants utilizing RFT and evaluated disease severity with an average accuracy of 96.4 ± 2.3%, an average mean absolute error of 0.065 ± 0.024, and a root mean square error of 0.080 ± 0.06. The results indicate that the proposed dual-stage model is exceptionally successful in the early detection and severity assessment of Parkinson's disease and demonstrates better efficacy than alternative models. [ABSTRACT FROM AUTHOR]

IntroductionThe expanded BRICS block presents significant opportunities for SMEs (Small and Medium Enterprises), but challenges related to financial literacy and digital access hinder their potential. While global efforts emphasize financial literacy and digitization as key drivers of economic growth, especially in developing regions, their specific impact on SMEs in the BRICS block remains underexplored. This paper contributes to the literature by contextualizing how financial literacy and digital financial access influence SME sustainability and economic progress, particularly in light of ongoing efforts to bridge the digital divide.MethodsUsing Principal Component Analysis to reduce dimensionality, the study uses advanced Random Forest Tree modeling, to evaluate current practices in SME finance, credit access, and digitization.ResultsResults indicate that both financial literacy and digitalization play pivotal roles in driving sustainable economic development, with significant implications for policy interventions aimed at supporting SME growth in emerging economies.DiscussionThis study addresses the crucial intersection of SME financial literacy and digital financial access, focusing on their role in fostering economic development within the expanded BRICS block-a group now comprising major emerging economies that collectively face substantial disparities in financial inclusion. The study results are relevant not only for understanding the BRICS context but also for shaping global strategies toward inclusive financial systems and SME resilience in the digital era.

Abstract Objective To investigate the effect of COVID-19 infection on pancreatic cancer. Methods Based on the mRNA-Seq data of COVID-19 patients and pancreatic cancer (PC) patients in the GEO database, we used a support vector machine (SVM), LASSO-Cox regression analysis and random forest tree (RF) to screen the common signature genes of the two diseases and further investigate their effects and functional characteristics on PC, respectively. The above procedures were performed in R software. Results The proteins COL10A1/FAP/FN1 were found to be common signature genes for COVID-19 and PC, were significantly up-regulated in both diseases and showed good diagnostic efficacy for PC. The risk model based on COL10A1/FAP/FN1 showed good PC risk prediction ability and clinical application potential. Tumor typing based on COL10A1/FAP/FN1 expression levels effectively classified PC into different subtypes and showed significant differences between the two subtypes in terms of survival prognosis, immune levels, immune checkpoint expression levels, mutation status of common tumor mutation sites, and drug sensitivity analysis. While pathway analysis also revealed that FN1 as an extracellular matrix component may be involved in the biological process of PC by regulating the PI3K-AKT signaling axis. Conclusion The upregulated expression of COL10A1/FAP/FN1, the characteristic genes of COVID-19, are potential diagnostic targets for PC, and the upregulated expression of FN1 may promote the progression of PC by activating the PI3K-AKT signaling pathway. The COL10A1/FAP/FN1-based typing provides a new typing approach for PC, and also provides a good reference and idea for the refinement of PC treatment and subsequent clinical research.

Objective: To investigate the effect of COVID-19 infection on pancreatic cancer. Methods: Based on the mRNA-Seq data of COVID-19 patients and pancreatic cancer (PC) patients in the GEO database, we used a support vector machine (SVM), LASSO-Cox regression analysis and random forest tree (RF) to screen the common signature genes of the two diseases and further investigate their effects and functional characteristics on PC, respectively. The above procedures were performed in R software. Results: The proteins COL10A1/FAP/FN1 were found to be common signature genes for COVID-19 and PC, were significantly up-regulated in both diseases and showed good diagnostic efficacy for PC. The risk model based on COL10A1/FAP/FN1 showed good PC risk prediction ability and clinical application potential. Tumor typing based on COL10A1/FAP/FN1 expression levels effectively classified PC into different subtypes and showed significant differences between the two subtypes in terms of survival prognosis, immune levels, immune checkpoint expression levels, mutation status of common tumor mutation sites, and drug sensitivity analysis. While pathway analysis also revealed that FN1 as an extracellular matrix component may be involved in the biological process of PC by regulating the PI3K-AKT signaling axis. Conclusion: The upregulated expression of COL10A1/FAP/FN1, the characteristic genes of COVID-19, are potential diagnostic targets for PC, and the upregulated expression of FN1 may promote the progression of PC by activating the PI3K-AKT signaling pathway. The COL10A1/FAP/FN1-based typing provides a new typing approach for PC, and also provides a good reference and idea for the refinement of PC treatment and subsequent clinical research. [ABSTRACT FROM AUTHOR]

Now days breast cancer has emerged as a diseases effecting women to suffer a life threating phase and eventually lead to death world wide. The prediction of breast cancer in woman at the initial stage can aggrandize recovery and chance of abidance considerably as the essential medical treatments can be adapted on time and stop its further growth. Moreover the precise categorization of tumor eliminates the avoidable treatments and patients skips from witnessing the medical emergencies. Thus the exact categorization of breast cancer either benign or malignant and the precised analysis of each is a matter of important exploration. Machine learning have extensively beneficial aspects in critical feature extraction from the breast cancer dataset. Thus the machine learning can be astronomically honored as a alternative methodology in breast cancer pattern categorization and forecast modeling. In this paper ML techniques namely Support vector machines, logistic Regression, Random forest tree and k-nearest neighbours (k-Nns) are over viewed and later performance measures compared for breast cancer analysis and prognosis. [ABSTRACT FROM AUTHOR]

Due to the teacher shortage in the U.S., an automatic toolbox with secondary development based on the ArcPy package was created to explore the spatial imbalance of the pupil–teacher ratio. It consists of four tools (or toolsets) for multi-scale spatial visualization, a sensitivity analysis with a heat map, the ordinary least squares regression with spatial autocorrelation, and the random forest tree regression. This study demonstrated the application of the toolset in the evaluation of educational resource spatial misallocation. Firstly, multi-scale analysis results showed that, the loss of teachers was mainly distributed in Oregon, Nevada, Arizona, and California from the state level, while it focused on such counties as Terrebonne Parish, Concordia Parish, and Bienville Parish in Louisiana in the county level. Secondly, it was found through heatmap sensitivity analysis that pupil–teacher ratios were highly related to low levels of student support services staff, free lunch programs, and low levels of local education agency (LEA) administrators. Then, the OLS tool was used to automatically calculate the spatial weighted matrix, the Moran I, R2, and AICC indices, AdjR2, F-Stat, F-Prob, and the Wald statistic, which showed whether the model was significant or not. This was followed by random forest tree regression modeling, which found that the LEA administrative support staff and the totally free lunch number highly impacted pupil–teacher ratios. Besides, the designed tool provided ribbons for the Common Core of Data (CCD) to link to other data sources. [ABSTRACT FROM AUTHOR]

Introduction: The expanded BRICS block presents significant opportunities for SMEs (Small and Medium Enterprises), but challenges related to financial literacy and digital access hinder their potential. While global efforts emphasize financial literacy and digitization as key drivers of economic growth, especially in developing regions, their specific impact on SMEs in the BRICS block remains underexplored. This paper contributes to the literature by contextualizing how financial literacy and digital financial access influence SME sustainability and economic progress, particularly in light of ongoing efforts to bridge the digital divide., Methods: Using Principal Component Analysis to reduce dimensionality, the study uses advanced Random Forest Tree modeling, to evaluate current practices in SME finance, credit access, and digitization., Results: Results indicate that both financial literacy and digitalization play pivotal roles in driving sustainable economic development, with significant implications for policy interventions aimed at supporting SME growth in emerging economies., Discussion: This study addresses the crucial intersection of SME financial literacy and digital financial access, focusing on their role in fostering economic development within the expanded BRICS block-a group now comprising major emerging economies that collectively face substantial disparities in financial inclusion. The study results are relevant not only for understanding the BRICS context but also for shaping global strategies toward inclusive financial systems and SME resilience in the digital era., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 M. V., Almuraqab, Moonesar, Braendle and Rao.)

Intrusion detection pretended to be a major technique for revealing the attacks and guarantee the security on the network. As the data increases tremendously every year on the Internet, a single algorithm is not sufficient for the network security. Because, deploying a single learning approach may suffer from statistical, computational and representational issues. To eliminate these issues, this paper combines multiple machine learning algorithms called stacked ensemble learning, to detect the attacks in a better manner than conventional learning, where a single algorithm is used to identify the attacks. The stacked ensemble system has been taken the benchmark data set, NSL-KDD, to compare its performance with other popular machine learning algorithms such as ANN, CART, random forest, SVM and other machine learning methods proposed by researchers. The experimental results show that stacked ensemble learning is a proper technique for classifying attacks than other existing methods. And also, the proposed system shows better accuracy compare to other intrusion detection models. [ABSTRACT FROM AUTHOR]

This study examined landslide susceptibility, an increasingly common problem in mountainous regions across the world as a result of urbanization, deforestation, and various natural processes. The Rangit River watershed in Sikkim Himalaya is one of the most landslide-prone areas in India. The main objective of this study was to produce landslide susceptibility maps of the Rangit River watershed using novel ensembles of random forest tree (RFT) with support vector machine (RFT-SVM), artificial neural network (RFT-ANN), naïve Bayes tree (RFT-NBT), and logistic model tree (RFT-LMT). An inventory of landslides was created using historical landslide data, government and scientific studies, and Google Earth's high-resolution satellite images. The landslide/non-landslide locations were split 70/30 for training and validating the models, respectively. Eleven landslide conditioning factors were selected based on their predictive ability, determined using the information gain method, and each factor's importance was derived. A landslide susceptibility index was then estimated by weighted overlay using a model builder in a GIS (Geographic Information System) environment. Based on the area under the curve and statistical metrics, RFT-LMT was identified as the best model. The results showed that approximately 40% of the Rangit River watershed has high to very high susceptibility to landslides. This study's findings will be useful for policy-makers and land use planners in managing and mitigating future landslides in the study area. [ABSTRACT FROM AUTHOR]

Mobile cloud computing offers computing, storage, and memory resources to mobile users through its high computing cloud servers. Mobile services are facilitated with efficient resource provisioning in the cloud. However, due to its inherent nature such as disconnections and limited battery life mobile users experience poor quality of service (QoS) in their connectivity with the cloud. This paper proposes an efficient request state aware resource provisioning technique that provisions the resources considering the current context information viz., battery, and connection quality of the mobile client. Various state viz., Accepted, Submitted and Running, Submitted and Paused, Resumed, Fulfilled, Rejected and Exit has been used to monitor the Client's state. Besides, an intelligent resource capacity prediction technique based on a random forest algorithm has been incorporated to predict the future resource capacity requirement and schedule the client's job in the cloud. The proposed technique has been implemented using CloudSim and analyzed using a mobile cloud storage dataset. Performance analysis proves that the proposed technique outperforms the state of art techniques in terms of waiting time, deadline violation, and accuracy of the prediction technique. [ABSTRACT FROM AUTHOR]

Complex metal oxides (CMOs) are used broadly in applications including electroreactive forms found in lithium-ion battery technology. Computational chemistry can provide unique information about how the properties of CMO cathode materials change in response to changes in stoichiometry, for example, changes of the lithium (Li) content during the charge–discharge cycle of the battery. However, this is difficult to measure experimentally due to the small cross-sectional area of the cations. Outside of operational conditions, the Li content can influence the transformations of the CMO when exposed to the environment. For example, metal release from CMOs in aqueous settings has been identified as a cross-cutting mechanism important to CMO degradation. Computational studies investigating metal release from CMOs show that the thermodynamics depend on the oxidation states of lattice cations, which is expected to vary with the lithium content. In this work, computational studies track changes in metal release trends as a function of Li content in Lix(Ni1/3Mn1/3Co1/3)O2 (NMC). The resulting dataset is used to construct a random forest tree (RFT) machine learning (ML) model. A modeling challenge in delithiation studies is the large configurational space to sample. Through investigating multiple configurations at each lithium fraction, we find structural features associated with favorable energies to chemically guide the identification of relevant structures and adequately predict voltage values. [ABSTRACT FROM AUTHOR]

Currently, the entire world is fighting against the Corona Virus (COVID-19). As of now, more than thirty lacs of people all over the world were died due to the COVID-19 till April 2021. A recent study conducted by China suggests that Chest CT and X-ray images can be used as a preliminary test for COVID detection. This paper propose a transfer learning-based mathematical COVID detection model, which integrates a pre-trained model with the Random Forest Tree (RFT) classifier. As the available COVID dataset is noisy and imbalanced so Principal Component Analysis (PCA) and Generative Adversarial Networks (GANs) is used to extract most prominent features and balance the dataset respectively. The Bayesian Cross-Entropy Loss function is used to penalize the false detection differently according to the class sensitivity (i.e., COVID patient should not be classified as Normal or Pneumonia class). Due to the small dataset, a pre-trained model like VGGNet-19, ResNet50 and Inception_ResNet_V2 were chosen to extract features and then trained them over the RFT for the classification task. The experiment results showed that ResNet50 gives the maximum accuracy of 99.51%, 98.21%, and 97.2% for training, validation, and testing phases, respectively, and none of the COVID Chest X-ray images were classified as Normal or Pneumonia classes. [ABSTRACT FROM AUTHOR]

Due to the teacher shortage in the U.S., an automatic toolbox with secondary development based on the ArcPy package was created to explore the spatial imbalance of the pupil–teacher ratio. It consists of four tools (or toolsets) for multi-scale spatial visualization, a sensitivity analysis with a heat map, the ordinary least squares regression with spatial autocorrelation, and the random forest tree regression. This study demonstrated the application of the toolset in the evaluation of educational resource spatial misallocation. Firstly, multi-scale analysis results showed that, the loss of teachers was mainly distributed in Oregon, Nevada, Arizona, and California from the state level, while it focused on such counties as Terrebonne Parish, Concordia Parish, and Bienville Parish in Louisiana in the county level. Secondly, it was found through heatmap sensitivity analysis that pupil–teacher ratios were highly related to low levels of student support services staff, free lunch programs, and low levels of local education agency (LEA) administrators. Then, the OLS tool was used to automatically calculate the spatial weighted matrix, the Moran I, R2, and AICC indices, AdjR2, F-Stat, F-Prob, and the Wald statistic, which showed whether the model was significant or not. This was followed by random forest tree regression modeling, which found that the LEA administrative support staff and the totally free lunch number highly impacted pupil–teacher ratios. Besides, the designed tool provided ribbons for the Common Core of Data (CCD) to link to other data sources.

Breast cancer is the most common cancer in women occurring worldwide. Some of the procedures used to diagnose breast cancer are mammogram, breast ultrasound, biopsy, breast magnetic resonance imaging, and blood tests such as complete blood count. Detecting breast cancer at an early stage plays an important role in diagnostic and curative procedures. This paper aims to develop a predictive model for detecting the breast cancer using blood samples data containing age, body mass index (BMI), glucose, insulin, homeostasis model assessment (HOMA), leptin, adiponectin, resistin, and chemokine monocyte chemoattractant protein 1 (MCP-1).The two main challenges encountered in this process are identification of biomarkers and the precision of disease prediction accuracy. The proposed methodology employs principal component analysis in a peculiar approach followed by random forest tree prediction model to discriminate between healthy and breast cancer patients. This approach extracts high communalities, a linear combination of input attributes in a systematic procedure as principal axis elements. The iteratively extracted principal axis elements combined with minimum number of input attributes are able to predict the disease with higher accuracy of classification with increased sensitivity and specificity score. The results proved that the proposed approach generates a higher predictor performance than the previous reported results by opting relevant extracted principal axis elements and attributes that commend the classifier with increased performance measures. [ABSTRACT FROM AUTHOR]

Offline handwritten character recognition is a part of the arduous area of research in the domain of document analysis and recognition. In order to enhance the recognition results of offline handwritten Gurumukhi characters, the authors have applied hybrid features and adaptive boosting approach in this paper. On feature extraction stage, zoning, diagonal, centroid, and peak extent-based features have been taken into account for extracting the meaningful information about each character. On the classification stage, three classifiers, namely decision tree, random forest, and convolution neural network classifier, are used. For experimental work, the authors have collected 14,000 pre-segmented samples of Gurumukhi characters (35-class problem) written by 400 writers where they have used 70% data as training set and remaining 30% data as testing set. The authors have also explored fivefold cross-validation technique for experimental work. The AdaBoost approach along with the fivefold cross-validation strategy outstands the existing techniques in the relevant field with the recognition accuracy of 96.3%. [ABSTRACT FROM AUTHOR]

Complex metal oxides (CMOs) are used broadly in applications including electroreactive forms found in lithium-ion battery technology. Computational chemistry can provide unique information about how the properties of CMO cathode materials change in response to changes in stoichiometry, for example, changes of the lithium (Li) content during the charge–discharge cycle of the battery. However, this is difficult to measure experimentally due to the small cross-sectional area of the cations. Outside of operational conditions, the Li content can influence the transformations of the CMO when exposed to the environment. For example, metal release from CMOs in aqueous settings has been identified as a cross-cutting mechanism important to CMO degradation. Computational studies investigating metal release from CMOs show that the thermodynamics depend on the oxidation states of lattice cations, which is expected to vary with the lithium content. In this work, computational studies track changes in metal release trends as a function of Li content in Lix(Ni1/3Mn1/3Co1/3)O2 (NMC). The resulting dataset is used to construct a random forest tree (RFT) machine learning (ML) model. A modeling challenge in delithiation studies is the large configurational space to sample. Through investigating multiple configurations at each lithium fraction, we find structural features associated with favorable energies to chemically guide the identification of relevant structures and adequately predict voltage values.

Students' orientation in public institutions and choosing their academic paths or their appropriate specialization is important to students to continue their studies Easily in their school career. Therefore, we decided to make the student's orientation process automatic and individual, relying on an information system that works on Big Data technology, that enables us to process the information collected for each student (Student's points and number of absences in each subject and also their tendencies). Then we used the algorithms of machine learning, that enable us to give the appropriate specialization to each student. In this paper, we compared the accuracy and execution time of the following algorithms (Naïve Bayes, SVM, Random Forest Tree and Neural Network), where we found that Naïve Bayes is the best for this system. [ABSTRACT FROM AUTHOR]

Suboptimal health status (SHS), a physical state between health and disease, is a subclinical and reversible stage of chronic disease. Previous studies have shown alterations in the intestinal microbiota in patients with some chronic diseases. This study aimed to investigate the association between SHS and intestinal microbiota in a case‐control study with 50 SHS individuals and 50 matched healthy controls. Intestinal microbiota was analysed by MiSeq 250PE. Alpha diversity of intestinal microbiota in SHS individuals was higher compared with that of healthy controls (Simpson index, W = 2238, P =.048). Beta diversity was different between SHS and healthy controls (P =.018). At the phylum level, the relative abundance of Verrucomicrobia was higher in the SHS group than that in the controls (W = 2201, P =.049). Compared with that of the control group, nine genera were significantly higher and five genera were lower in abundance in the SHS group (all P <.05). The intestinal microbiota, analysed by a random forest model, was able to distinguish individuals with SHS from the controls, with an area under the curve of 0.79 (95% confidence interval: 0.77‐0.81). We demonstrated that the alteration of intestinal microbiota occurs with SHS, an early stage of disease, which might shed light on the importance of intestinal microbiota in the primary prevention of noncommunicable chronic diseases. [ABSTRACT FROM AUTHOR]

Blasting is one of the primary mining operations for extracting minerals and ores however, if not designed properly, may have a varying degree of environmental and socio-economic impact in and around mining areas. In Indian mining industry, blast designs are fundamentally based on the experience and capability of the blasting crew and its assessment is more qualitative in nature, based on conventional trial and error basis. With the change in site geology and geotechnical parameters, the blast design parameters also require alterations, which can be standardized with the development of an intelligent system such as neural network. In this paper, the concept of artificial neural network and random forest algorithm has been used for better blast designs. Over 120 blast results from an opencast coal mine have been used for prediction of burden and energy factor with blast hole diameter, bench height to stemming ratio, nature of strata and average fragment size as input parameters. Out of 120 data sets 85 data sets recorded at a surface coal mine was used to train the model and 20 for the validation. Co-efficient of determination and root mean square error was chosen as the indicators to identify the optimum neural network and random forest model. The root mean square values obtained for energy factor is 0.153 while it is 0.1947 for burden. Similarly, the RMSE values obtained using random forest tree algorithm is 0.48 for burden while 50.76 for energy factor. The results revealed that random forest tree network system has potential to design better blast that is not generic and can be a potential tool for blasting engineers to design optimum blast for the mines. [ABSTRACT FROM AUTHOR]

Automatic modulation recognition (AMR) is becoming more important because it is usable in advanced general-purpose communication such as, cognitive radio, as well as, specific applications. Therefore, developments should be made for widely used modulation types; machine learning techniques should be employed for this problem. In this study, we have evaluated performances of different machine learning algorithms for AMR. Specifically, we have evaluated performances of artificial neural networks, support vector machines, random forest tree, k-nearest neighbor, Hoeffding tree, logistic regression, Naive Bayes and Gradient Boosted Regression Tree methods to obtain comparative results. The most preferred feature extraction methods in the literature have been used for a set of modulation types for general-purpose communication. We have considered AWGN and Rayleigh channel models evaluating their recognition performance as well as having made recognition performance improvement over Rayleigh for low SNR values using the reception diversity technique. We have compared their recognition performance in the accuracy metric, and plotted them as well. Furthermore, we have served confusion matrices for some particular experiments. [ABSTRACT FROM AUTHOR]

Assessment of mineral liberation spectrum with all its aspects is essential for plant control and optimization. This paper aims to estimate 2D mineral map and its associated liberation spectrum of a particular chromite sample from optical micrographs by using Random Forest Classification, a powerful machine-learning algorithm implemented on a user-friendly and an open-source software. This supervised classification method can be used to accurately generate 2D mineral map of this chromite sample. The variation of the measured spectra with the sample size is studied, showing that images of 200 particles randomly selected from the optical micrographs are sufficient to reproduce liberation spectrum of this sample. In addition, the 2D spectrum obtained with this classification method is compared with the one obtained from the Mineral Liberation Analyzer (MLA). Although 2D mineralogical compositions obtained by the two methods are quite similar, microscopic analysis estimates poorer liberation than MLA due to the residual noise (misclassified gangue) generated by the classification. Nevertheless, we cannot compare the reliabilities of the two methods, as there is not a standard produce yet to quantify the accuracy of MLA analysis. [ABSTRACT FROM AUTHOR]

Oral squamous cell carcinoma (OSCC) diagnosis through computer vision approach is newly introduced technique in the modern diagnostic era. Mitotic cell count from related tissue histopathological images signifies the proliferative marker of cancer cell has been recognized as an essential phenomenon in diagnosis. This paper aims at developing an automated technique for accomplishing the task of mitotic cell count from related histopathological images. In this regard, a new machine learning based methodology incorporating random forest tree classifier learns over four entropy measures, fractal dimension, and seven Hu's moments based descriptors have been introduced. The performance validation summarizes that proposed methodology can detect mitotic cell efficiently from histopathological images of OSCC with 89% precision, 95% recall or sensitivity, 97.35% specificity, 96.92% accuracy, 96.45% AUC and 92% F-score measure. [ABSTRACT FROM AUTHOR]

Massive dataset can be analyzed by establishing physical distributed environment or by hiring cloud-based distributed environment. The advantage of cloud-based environment over physical environment is that, it provides scalable virtual resources on demand and thus makes it suitable for handling increase in volume of the data. The various hidden patterns in data can provide knowledge bases for decision making. The statistical or data mining based methods can be used for finding knowledge patterns. Among the decision tree based classification algorithms, implementable in distributed environment, an efficient algorithm can be selected based on few parameters such as execution time, accuracy of prediction and complexity of the tree structure. In this study, Apache Hadoop-based distributed environment is established on virtual machine. Apache Spark is installed to execute machine learning algorithms. The comparative study of binary classification methods such as decision tree, gradient boosted tree and random forest tree is performed to judge their performances on the basis of defined parameters. It is found that Random forest tree performs best among all three algorithms for the considered dataset. [ABSTRACT FROM AUTHOR]

Data from a naturalistic driving study was used to examine foot placement during routine foot pedal movements and possible pedal misapplications. The study included four weeks of observations from 30 drivers, where pedal responses were recorded and categorized. The foot movements associated with pedal misapplications and errors were the focus of the analyses. A random forest algorithm was used to predict the pedal application types based the video observations, foot placements, drivers’ characteristics, drivers’ cognitive function levels and anthropometric measurements. A repeated multinomial logit model was then used to estimate the likelihood of the foot placement given various driver characteristics and driving scenarios. The findings showed that prior foot location, the drivers’ seat position, and the drive sequence were all associated with incorrect foot placement during an event. The study showed that there is a potential to develop a driver assistance system that can reduce the likelihood of a pedal error. [ABSTRACT FROM AUTHOR]

Real Estate / Land is the least straight-forward industry in our society. House costs keep changing everyday consistently and from time to time are publicized instead of being established on valuation. House estimation process is a critical purpose of land which can be used to gain profits. The composition tries to get supportive gaining from valid data of property markets. Computer based intelligence strategies are applied to explore evident property trades to discover profitable models for house buyers and vendors. For evaluating the cost various regression techniques were attempted and one with most raised exactness is used. [ABSTRACT FROM AUTHOR]

Wuhan was the first city to adopt the lockdown measures to prevent COVID-19 spreading, which improved the air quality accordingly. This study investigated the variations in chemical compositions, source contributions, and regional transport of fine particles (PM 2.5) during January 23–February 22 of 2020, compared with the same period in 2019. The average mass concentration of PM 2.5 decreased from 72.9 μg m−3 (2019) to 45.9 μg m−3 (2020), by 27.0 μg m−3. It was predominantly contributed by the emission reduction (92.0%), retrieved from a random forest tree approach. The main chemical species of PM 2.5 all decreased with the reductions ranging from 0.85 μg m−3 (chloride) to 9.86 μg m−3 (nitrate) (p < 0.01). Positive matrix factorization model indicated that the mass contributions of seven PM 2.5 sources all decreased. However, their contribution percentages varied from −11.0% (industrial processes) to 8.70% (secondary inorganic aerosol). Source contributions of PM 2.5 transported from potential geographical regions showed reductions with mean values ranging from 0.22 to 4.36 μg m−3. However, increased contributions of firework burning, secondary inorganic aerosol, road dust, and vehicle emissions from transboundary transport were observed. This study highlighted the complex and nonlinear response of chemical compositions and sources of PM 2.5 to air pollution control measures, suggesting the importance of regional-joint control. Unlabelled Image • Differences in PM 2.5 chemical species and sources since lockdown were reported. • Primary emission reduced while secondary formation enhanced since lockdown. • Emission reduction dominated the improvement of air quality in Wuhan during lockdown. [ABSTRACT FROM AUTHOR]