Search

Background: Rapid diagnosis of microbes in the burn wound is a big challenge in the medical field. Traditional biochemical detection techniques take hours or days to identify the species of contaminating and drug-resistant microbes. Near-infrared spectroscopy (NIRS) is evaluated to address the need for a fast and sensitive method for the detection of bacterial contamination in liquids.Methods: Herin, we developed a novel technique which by using NIRS together with supporting vector machine (SVM), to identify the microbial species and drug-resistant microbes in LB medium, and to diagnose the wound colonization and wound infection models of pigs.Results: The device could recognize 100% of seven kinds of microbes and 99.47% of the multi-drug resistant Staphylococcus aureus (S. aureus), with a concentration of 109 cfu ml-1 in LB medium. The accuracy of the microbial identification in colonized and infected wounds in-situ was 100%. The detection limit of NIRS with SVM for the detection of S. aureus and Escherichia coli (E. coli) was 101 cfu ml-1 in LB medium. Identification time was less than 5 s.Conclusion: Our findings validate for the first time a novel technique aimed at the rapid, noncontacted, highly sensitive, and specific recognition of several microbial species including drug-resistant ones. This technique could represent a promising approach to identify diverse microbial species and a potential bedside device to rapidly diagnose infected wounds. [ABSTRACT FROM AUTHOR]

Electrocardiogram (ECG) monitoring systems are widely applied to tele-cardiology healthcare programs nowadays, where ECG signals should always be compressed first during its transmission and storage. Previous studies attempted to achieve high quality decompressed signal with compression ratio as high as possible. In this paper, we investigated the performance on ECG arrhythmia classification on ECG signal decompressed after lossy compression with a high compression ratio. We proposed a simple but efficient method utilizing singular value decomposition (SVD) to decompose ECG signals, then applied the decompressed data to a convolutional neural network (CNN) and supporting vector machine (SVM) for classification. Using the optimization method with accuracy and compression ratio as objective functions, the highest average accuracy obtained is above 96% when the selected number of singular value is only 3. The evaluation results illustrated that the decompressed ECG signal even with a relatively high distortion can still achieve a satisfying performance in the arrhythmia classification.Thus,we proved that the real-time nature of the remote mobile ECG monitoring system can be greatly improved and countless people who are in need of ECG diagnosis can benefit from it.

Phishing attacks are increasing and it becomes necessary to use appropriate response methods and to respond effectively to phishing attacks. This paper aims to uncover phishing attack sites by analyzing a three-module set to prevent damage and reconsider the awareness of phishing attacks. Based on the analyzed content, a countermeasure was proposed for each type of phishing attack by using website features. These features will be classified in order to determine the effectiveness of the countermeasure. Finally, the proposed method enhanced the site security as anti-phishing technology. The phishing detection used three classification algorithms, which are the decision tree; the supporting vector machine and the random forest were combined into one system that was proposed in this paper for the purpose of obtaining the highest accuracy in detecting phishing sites. The results of the proposed algorithm showed 98.52% higher accuracy than others. [ABSTRACT FROM AUTHOR]

The rainfall prediction is important for metrological department as it closely associated with our environment and human life. An accuracy of rainfall prediction has great important for countries like India whose economy is dependent on agriculture. Because of dynamic nature of atmosphere, statistical techniques fail to predict rainfall information. The process of support vector machine (SVM) is to find an optimal boundary also known as hyper plane in which separates the samples (examples in a dataset) of different classes by a maximum margin. The proposed model uses the dynamic integrated model for exploring and learning large amount of data set. Balanced communication-avoiding support vector machine (CA-SVM) prediction model is proposed to achieve better performance and accuracy with limited number of iteration without any error. The rain fall dataset is used for performance evaluation. The proposed model starts with independent sample to the integrated samples without any collision in prediction. The proposed algorithm achieves 89% of accuracy when compared to the existing algorithms. The simulations demonstrate that prediction models indicate that the performance of the proposed algorithm Balanced CA-SVM has much better accuracy than the local learning model based on a set of experimental data if other things are equal. On the other hand, simulation results demonstrate the effectiveness and advantages of the Balanced CA-SVM model used in machine learning and further promises the scope for improvement as more and more relevant attributes can be used in predicting the dependent variables. [ABSTRACT FROM AUTHOR]

Antimicrobial peptides (AMPs) are considered as potential substitutes of antibiotics in the field of new anti-infective drug design. There have been several machine learning algorithms and web servers in identifying AMPs and their functional activities. However, there is still room for improvement in prediction algorithms and feature extraction methods. The reduced amino acid (RAA) alphabet effectively solved the problems of simplifying protein complexity and recognizing the structure conservative region. This article goes into details about evaluating the performances of more than 5,000 amino acid reduced descriptors generated from 74 types of amino acid reduced alphabet in the first stage and the second stage to construct an excellent two-stage classifier, Identification of Antimicrobial Peptides by Reduced Amino Acid Cluster (iAMP-RAAC), for identifying AMPs and their functional activities, respectively. The results show that the first stage AMP classifier is able to achieve the accuracy of 97.21 and 97.11% for the training data set and independent test dataset. In the second stage, our classifier still shows good performance. At least three of the four metrics, sensitivity (SN), specificity (SP), accuracy (ACC), and Matthews correlation coefficient (MCC), exceed the calculation results in the literature. Further, the ANOVA with incremental feature selection (IFS) is used for feature selection to further improve prediction performance. The prediction performance is further improved after the feature selection of each stage. At last, a user-friendly web server, iAMP-RAAC, is established at http://bioinfor.imu.edu.cn/iampraac.

Antimicrobial peptides (AMPs) are considered as potential substitutes of antibiotics in the field of new anti-infective drug design. There have been several machine learning algorithms and web servers in identifying AMPs and their functional activities. However, there is still room for improvement in prediction algorithms and feature extraction methods. The reduced amino acid (RAA) alphabet effectively solved the problems of simplifying protein complexity and recognizing the structure conservative region. This article goes into details about evaluating the performances of more than 5,000 amino acid reduced descriptors generated from 74 types of amino acid reduced alphabet in the first stage and the second stage to construct an excellent two-stage classifier, Identification of Antimicrobial Peptides by Reduced Amino Acid Cluster (iAMP-RAAC), for identifying AMPs and their functional activities, respectively. The results show that the first stage AMP classifier is able to achieve the accuracy of 97.21 and 97.11% for the training data set and independent test dataset. In the second stage, our classifier still shows good performance. At least three of the four metrics, sensitivity (SN), specificity (SP), accuracy (ACC), and Matthews correlation coefficient (MCC), exceed the calculation results in the literature. Further, the ANOVA with incremental feature selection (IFS) is used for feature selection to further improve prediction performance. The prediction performance is further improved after the feature selection of each stage. At last, a user-friendly web server, iAMP-RAAC, is established at http://bioinfor.imu.edu.cn/iampraac. [ABSTRACT FROM AUTHOR]

Machine learning (ML) methods have shown promising results in identifying genes when applied to large transcriptome datasets. However, no attempt has been made to compare the performance of combining different ML methods together in the prediction of high feed efficiency (HFE) and low feed efficiency (LFE) animals. In this study, using RNA sequencing data of five tissues (adrenal gland, hypothalamus, liver, skeletal muscle, and pituitary) from nine HFE and nine LFE Nellore bulls, we evaluated the prediction accuracies of five analytical methods in classifying FE animals. These included two conventional methods for differential gene expression (DGE) analysis (t -test and edgeR) as benchmarks, and three ML methods: Random Forests (RFs), Extreme Gradient Boosting (XGBoost), and combination of both RF and XGBoost (RX). Utility of a subset of candidate genes selected from each method for classification of FE animals was assessed by support vector machine (SVM). Among all methods, the smallest subsets of genes (117) identified by RX outperformed those chosen by t -test, edgeR, RF, or XGBoost in classification accuracy of animals. Gene co-expression network analysis confirmed the interactivity existing among these genes and their relevance within the network related to their prediction ranking based on ML. The results demonstrate a great potential for applying a combination of ML methods to large transcriptome datasets to identify biologically important genes for accurately classifying FE animals. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Engineering for Thermal Energy & Power / Reneng Dongli Gongcheng is the property of Journal of Engineering for Thermal Energy & Power and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This paper adopts a novel approach of Support Vector Machine (SVM) to forecast residential housing prices. as one type of machine learning algorithm, the proposed SVM encompasses a larger set of variables that are recognized as price-influencing and meanwhile enables recognizing the geographical pattern of housing price dynamics. The analytical framework consists of two steps. The first step is to identify the supporting vectors (SVs) to price variances using the stepwise multi-regression approach; and then it is to forecast the housing price variances by employing the SVs identified by the first step as well as other variables postulated by the hedonic price theory, where the housing prices in Taipei City are empirically examined to verify the designed framework. Results computed by nonparametric estimation confirm that the prediction power of using SVM in housing price forecasting is of high accuracy. Further studies are suggested to extract the geographical weights using kernel density estimates to reflect price responses to local quantiles of hedonic attributes.

This paper is focused on designing a cost function of selecting a foothold for a physical quadruped robot walking on rough terrain. The quadruped robot is modeled with Denavit–Hartenberg (DH) parameters, and then a default foothold is defined based on the model. Time of Flight (TOF) camera is used to perceive terrain information and construct a 2.5D elevation map, on which the terrain features are detected. The cost function is defined as the weighted sum of several elements including terrain features and some features on the relative pose between the default foothold and other candidates. It is nearly impossible to hand-code the weight vector of the function, so the weights are learned using Supporting Vector Machine (SVM) techniques, and the training data set is generated from the 2.5D elevation map of a real terrain under the guidance of experts. Four candidate footholds around the default foothold are randomly sampled, and the expert gives the order of such four candidates by rotating and scaling the view for seeing clearly. Lastly, the learned cost function is used to select a suitable foothold and drive the quadruped robot to walk autonomously across the rough terrain with wooden steps. Comparing to the approach with the original standard static gait, the proposed cost function shows better performance.

Copyright of Journal of Engineering for Thermal Energy & Power / Reneng Dongli Gongcheng is the property of Journal of Engineering for Thermal Energy & Power and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This paper adopts a novel approach of Support Vector Machine (SVM) to forecast residential housing prices. as one type of machine learning algorithm, the proposed SVM encompasses a larger set of variables that are recognized as price-influencing and meanwhile enables recognizing the geographical pattern of housing price dynamics. The analytical framework consists of two steps. The first step is to identify the supporting vectors (SVs) to price variances using the stepwise multi-regression approach; and then it is to forecast the housing price variances by employing the SVs identified by the first step as well as other variables postulated by the hedonic price theory, where the housing prices in Taipei City are empirically examined to verify the designed framework. Results computed by nonparametric estimation confirm that the prediction power of using SVM in housing price forecasting is of high accuracy. Further studies are suggested to extract the geographical weights using kernel density estimates to reflect price responses to local quantiles of hedonic attributes. [ABSTRACT FROM AUTHOR]

According to urban train running status, this paper adjusts constraints, air spring and lateral damper components running status and vibration signals of vertical acceleration of the vehicle body, combined with characteristics of urban train operation, we build an optimized train operation adjustment model and put forward corresponding estimation method-- wavelet packet energy moment, for the train state. First, we analyze characteristics of the body vertical vibration, conduct wavelet packet decomposition of signals according to different conditions and different speeds, and reconstruct the band signal which with larger energy; we introduce the hybrid ideas of particle swarm algorithm, establish fault diagnosis model and use improved particle swarm algorithm to solve this model; the algorithm also gives specific steps for solution; then calculate features of each band wavelet packet energy moment. Changes of wavelet packet energy moment with different frequency bands reflect changes of the train operation state; finally, wavelet packet energy moments with different frequency band are composed as feature vector to support vector machines for fault identification. [ABSTRACT FROM AUTHOR]

Knowledge of protein-ATP interaction can help for protein functional annotation and drug discovery. Accurately identifying protein-ATP binding residues is an important but challenging task to gain the knowledge of protein-ATP interactions, especially for the case where only protein sequence information is given. In this study, we propose a novel method, named DeepATPseq, to predict protein-ATP binding residues without using any information about protein three-dimension structure or sequence-derived structural information. In DeepATPseq, the HHBlits-generated position-specific frequency matrix (PSFM) profile is first employed to extract the feature information of each residue. Then, for each residue, the PSFM-based feature is fed into two prediction models, which are generated by the algorithms of deep convolutional neural network (DCNN) and support vector machine (SVM) separately. The final ATP-binding probability of the corresponding residue is calculated by the weighted sum of the outputted values of DCNN-based and SVM-based models. Experimental results on the independent validation data set demonstrate that DeepATPseq could achieve an accuracy of 77.71%, covering 57.42% of all ATP-binding residues, while achieving a Matthew's correlation coefficient value (0.655) that is significantly higher than that of existing sequence-based methods and comparable to that of the state-of-the-art structure-based predictors. Detailed data analysis show that the major advantage of DeepATPseq lies at the combination utilization of DCNN and SVM that helps dig out more discriminative information from the PSFM profiles. The online server and standalone package of DeepATPseq are freely available at: https://jun-csbio.github.io/DeepATPseq/ for academic use. [Display omitted] • DeepATPseq is a novel method for predicting protein-ATP binding residues using position-specific frequency matrix. • The combination utilization of DCNN and SVM helps to dig out more discriminative information from the PSFM profiles. • DeepATPseq could achieve a higher performance than the existing sequence-based methods. [ABSTRACT FROM AUTHOR]

As the number of trips along the Arctic route has increased, the safe navigation of icebreakers on this route has become vital. One of the key factors that affect the stability of an icebreaker is the ice thickness in the route. The ice thickness, if measured in real time during navigation, can aid in the construction of an ice map or can be used for the structural analysis of the icebreaker after the voyage. However, the measurement of ice thickness during the voyage is challenging. In this study, a method to improve the measurement of ice thickness from an image is introduced. To measure the ice thickness accurately and quickly, a method to identify the lower boundary curve of the cross-section of an ice patch is developed. Pixel-based constraints are determined by considering the characteristics of color variation in an image. In this method, the lower boundary curve is determined by using image convolution and a specific filter, and the performance efficiency is enhanced through a machine learning technique. The results suggest that an accumulating learning process can increase the recognition rate. • A method to identify the lower boundary curve of the cross-section of an ice patch. • Indirect way to measure the ice thickness in ice regions. • Lower boundary curve determined by using image convolution and a specific filter. • Enhanced performance efficiency through a machine learning technique, SVM. [ABSTRACT FROM AUTHOR]

This paper is focused on designing a cost function of selecting a foothold for a physical quadruped robot walking on rough terrain. The quadruped robot is modeled with Denavit–Hartenberg (DH) parameters, and then a default foothold is defined based on the model. Time of Flight (TOF) camera is used to perceive terrain information and construct a 2.5D elevation map, on which the terrain features are detected. The cost function is defined as the weighted sum of several elements including terrain features and some features on the relative pose between the default foothold and other candidates. It is nearly impossible to hand-code the weight vector of the function, so the weights are learned using Supporting Vector Machine (SVM) techniques, and the training data set is generated from the 2.5D elevation map of a real terrain under the guidance of experts. Four candidate footholds around the default foothold are randomly sampled, and the expert gives the order of such four candidates by rotating and scaling the view for seeing clearly. Lastly, the learned cost function is used to select a suitable foothold and drive the quadruped robot to walk autonomously across the rough terrain with wooden steps. Comparing to the approach with the original standard static gait, the proposed cost function shows better performance. [ABSTRACT FROM AUTHOR]