Vector Machine Based Classification Model Research Articles

Qualitative and quantitative chemometric modelling of nanostructured carbon samples based on infrared spectroscopy

Rapid population growth necessitates a continuous increase in industrial productivity, with a concomitant environmental burden. During the past few years, nanostructured carbon materials have proved their effectiveness in reducing the usage of several hazardous substances, owing to their distinct characteristics. These properties depend on the type of feedstock and the parameters of pyrolysis. We have developed multivariate prediction models to determine several physical properties of nanostructured carbon samples, which are usually calculated from the adsorption isotherms. Adsorption measurement is a time-consuming and exhaustive process. Therefore, our goal was to provide a fast and environmentally friendly alternative to current methods to determine micropore volume, specific surface area and total pore volume, based on FTIR spectroscopy coupled with chemometric methods. Moreover, we have created classification models, which are capable of predicting the used feedstock materials from IR spectra. Our support vector machine–based classification model had the best accuracy values, above 0.86. Our classification and regression models have excellent performance and were properly validated, thus they are good alternatives for the robust and fast determination of the important qualitative and quantitative features of carbon samples.

Identification of polar liquids using support vector machine based classification model

<div align="left">The dispersive nature of polar liquids creates ambiguity in their identification process. It requires a long time and effort to compare the measured values with the available standard values to identify the unknown liquid. Nowadays machine learning techniques are being used widely to assist the measurement techniques and make predictions with great accuracy and less human effort. This paper proposes a support vector machine (SVM) based classification model for the identification of six polar liquids- butan-1-ol, dimethyl sulphoxide, ethanediol, ethanol, methanol and propan-1-ol for a temperature range of 10 °C–50 °C and frequency range of 0.1 GHz – 5 GHz. The model is constructed using the data from the National Physical Laboratory (NPL) report MAT 23. The identification of unknown liquid is based on complex permittivity measurement. If the measurement error in complex permittivity is less than ±6% of the standard value in NPL report, the proposed model identifies the liquids with 100% accuracy in the entire temperature and frequency range. The performance of the model is validated by testing the model with data external to the dataset used. The findings show that the proposed model is a useful and efficient tool for identifying unknown polar liquids.</div>

An Efficient Coding Network Based Feature Extraction with Support Vector Machine Based Classification Model for CT Lung Images

Lung cancer is a serious illness affects people all over the globe. To increase the survival rate of patients affected by lung cancer, in advance recognition of lung cancer with effective treatments is important. This study introduces a new deep learning (DL) based feature extraction and classification technique for CT lung images. A DL model using Coding Network (CN) is presented for the extraction of high-level features and classical features. Initially, the convolution neural network is trained as a coding network and the actual pixels are coded into feature vectors for representing the high-level concepts for classification. Next, an extraction of chosen classical features takes place depending upon background knowledge of lung CT images. In addition, an automatic feature fusion takes place to avoid annoying parameter choice. Besides, support vector machine (SVM) model is employed for classify CT lung images in an effective way. For experimentation, a benchmark dataset is utilized to appraise the outcome of the presented CN-SVM model and is validated under several dimensions.

An optimal support vector machine based classification model for sentimental analysis of online product reviews

In present days, recent developments in data analytics take place that allows the identification of underlining trends through effective computational models. In several e-commerce and social platform, massive number of online product reviews is posted by end users that significantly help the developers with priceless insight while designing the products. This paper presents a new cluster based classification model for online product reviews. The presented model comprises several processes. Initially, support vector machine (SVM) based classification model is applied to classify the product reviews. Then, confusion matrix is generated to consider the possibilities of every consumer purchasing the product. Next, K-means clustering technique is applied to cluster the available data into two groups. At the next stage, sentimental analysis approach is employed to extracting the features. Finally, fuzzy based soft set theory is applied to determine the possibility of the customer to purchase the product effectively. The experimental validation of the presented model takes place on ipod dataset. The simulation outcome pointed out the superior characteristics of the presented model under several aspects.

Identification of potential histone deacetylase1 (HDAC1) inhibitors using multistep virtual screening approach including SVM model, pharmacophore modeling, molecular docking and biological evaluation

Histone Deacetylases (HDACs) play a significant role in the regulation of gene expression by modifying histones and non-histone substrates. Since they are key regulators in the reversible epigenetic mechanism, they are considered as promising drug targets for the treatment of various cancers. In the present study, we have developed a workflow for identification of HDAC1 inhibitors using a multistage virtual screening approach from Maybridge and Chembridge chemical library. Initially, a support vector machine based classification model was generated, followed by generation of a zinc-binding group (ZBG) based pharmacophore model. The hits screened from these models were further subjected to molecular docking. Finally, a set of twenty-three molecules were selected from Maybridge and Chembridge library. The biological evaluation of these hits revealed that three out of the twenty-three tested compounds are showing HDAC1 inhibition along with the moderate anti-proliferative activity. It was found that the identified inhibitors are exerting chromosomal loss effect in growing yeast cells. Further, to extend the activity spectrum of the identified inhibitors, the optimization guidelines were drawn with the hydration site mapping approach by using in silico tool Watermap.Communicated by Ramaswamy H. Sarma

Abnormal Resting-State Functional Connectivity in the Whole Brain in Lifelong Premature Ejaculation Patients Based on Machine Learning Approach.

Recent neuroimaging studies have indicated that abnormalities in brain structure and function may play an important role in the etiology of lifelong premature ejaculation (LPE). LPE patients have exhibited aberrant cortical structure, altered brain network function and abnormal brain activation in response to erotic pictures. However, it remains unclear whether resting-state whole brain functional connectivity (FC) is altered in LPE patients. Machine learning analysis has the advantage of screening the best classification features from high-throughput data (such as FC), which has the potential to identify the pathophysiological targets of disease by establishing classification indicators for patients and healthy controls (HCs). Therefore, the supported vector machine based classification model using FC as features was used in the present study to confirm the most specific FCs that distinguish LPE patients from healthy controls. After feature selection, the remained features were used to build the classification model, with an accuracy 0.85 ± 0.14, sensitivity of 0.92 ± 0.18, specificity of 0.72 ± 0.30, and recall index of 0.85 ± 0.17 across 1000 testing groups (100 times 10-folds cross validation). After that, two-sample t-tests with family-wise error correction were used to compare these features that occur more than 500 times during training steps between LPE patients and HCs. Four FCs, (1) between left medial part of orbital frontal cortex (mOFC) and right mOFC, (2) between the left rectus and right postcentral gyrus, (3) between the right insula and left pallidum, and (4) between the right middle part of temporal pole and right inferior part of temporal gyrus showed significant group difference. These results demonstrate that resting-state brain FC might be a discriminating feature to distinguish LPE patients from HCs. These classification features, especially the FC between bilateral mOFC, provide underlying abnormal central functional targets in LPE etiology, which offers a novel alternative target for future intervention in LPE treatment.

Towards the use of diffuse reflectance spectroscopy for real-time in vivo detection of breast cancer during surgery

BackgroundBreast cancer surgeons struggle with differentiating healthy tissue from cancer at the resection margin during surgery. We report on the feasibility of using diffuse reflectance spectroscopy (DRS) for real-time in vivo tissue characterization.MethodsEvaluating feasibility of the technology requires a setting in which measurements, imaging and pathology have the best possible correlation. For this purpose an optical biopsy needle was used that had integrated optical fibers at the tip of the needle. This approach enabled the best possible correlation between optical measurement volume and tissue histology. With this optical biopsy needle we acquired real-time DRS data of normal tissue and tumor tissue in 27 patients that underwent an ultrasound guided breast biopsy procedure. Five additional patients were measured in continuous mode in which we obtained DRS measurements along the entire biopsy needle trajectory. We developed and compared three different support vector machine based classification models to classify the DRS measurements.ResultsWith DRS malignant tissue could be discriminated from healthy tissue. The classification model that was based on eight selected wavelengths had the highest accuracy and Matthews Correlation Coefficient (MCC) of 0.93 and 0.87, respectively. In three patients that were measured in continuous mode and had malignant tissue in their biopsy specimen, a clear transition was seen in the classified DRS measurements going from healthy tissue to tumor tissue. This transition was not seen in the other two continuously measured patients that had benign tissue in their biopsy specimen.ConclusionsIt was concluded that DRS is feasible for integration in a surgical tool that could assist the breast surgeon in detecting positive resection margins during breast surgery.Trail registration NIH US National Library of Medicine–clinicaltrails.gov, NCT01730365. Registered: 10/04/2012 https://clinicaltrials.gov/ct2/show/study/NCT01730365

Automated Neuron Detection in High-Content Fluorescence Microscopy Images Using Machine Learning.

The study of neuronal morphology in relation to function, and the development of effective medicines to positively impact this relationship in patients suffering from neurodegenerative diseases, increasingly involves image-based high-content screening and analysis. The first critical step toward fully automated high-content image analyses in such studies is to detect all neuronal cells and distinguish them from possible non-neuronal cells or artifacts in the images. Here we investigate the performance of well-established machine learning techniques for this purpose. These include support vector machines, random forests, k-nearest neighbors, and generalized linear model classifiers, operating on an extensive set of image features extracted using the compound hierarchy of algorithms representing morphology, and the scale-invariant feature transform. We present experiments on a dataset of rat hippocampal neurons from our own studies to find the most suitable classifier(s) and subset(s) of features in the common practical setting where there is very limited annotated data for training. The results indicate that a random forests classifier using the right feature subset ranks best for the considered task, although its performance is not statistically significantly better than some support vector machine based classification models.

Bias, accuracy and sample size in the systematic linking of historical records

IntroductionLinking distinct historical sources on an automated basis directs attention to the quality and representativeness of the linked data created by these systems. Linking with time-invariant personal characteristics arguably minimizes bias or departures from representativeness even though a wider set of features might generate more links.
 Objectives and ApproachThe objective of this research is to compare, evaluate and understand bias when two linking methodologies are employed on the same data sources. Our approach to studying this problem is by comparing linked records from Canadian censuses (linking 1871 to 1881) generated by two different linking strategies. The first method is a support vector machine based classification model on time-invariant individual characteristics. Using this method a large number of multiple matches is generated, as records look similar on a small number of time-invariant individual characteristics. The second method adds a second stage of disambiguating multiple matches using family information.
 ResultsWe compare the links produced by the two methods used in the study and we discuss the results. The comparison is in terms of number of links produced, their quality (false positive rate) and the bias of the linked data produced. A complication is that there are many dimensions of bias. Even time-invariant criteria typically generate some bias.
 As expected, the two-step process produces a larger linked sample. Interestingly, it also produces a lower error rate and different patterns of bias. Both methods understate the Quebec-born, French-ethnicity, the unmarried and adolescents. Unexpectedly, the bias in favour of married people is larger using individual (first method) than family information (second method). However, family-based linking does over-represent young children.
 Conclusion/ImplicationsResults suggest that neither method will be universally preferable. Rather, the choice of research question may affect the preferred balance of biases and link rate. Fortunately, the advance of computational capacity allows a researcher to select a method that generate links most appropriate for the problem at hand.

Automatic extraction and visualization of semantic relations between medical entities from medicine instructions

Recent years have witnessed the rapid development and tremendous research interests in healthcare domain. The health and medical knowledge can be acquired from many sources, such as professional health providers, health community generated data and textual descriptions of medicines. This paper explores the classification and extraction of semantic relation between medical entities from the unstructured medicine Chinese instructions. In this paper, three kinds of textual features are extracted from medicine instruction according to the nature of natural language texts. And then, a support vector machine based classification model is proposed to categorize the semantic relations between medical entities into the corresponding semantic relation types. Finally, the extraction algorithm is utilized to obtain the semantic relation triples. This paper also visualizes the semantic relations between medical entities with relationship graph for their future processing. The experimental results show that the approach proposed in this paper is effective and efficient in the classification and extraction of semantic relations between medical entities.

Friction stir weld classification by applying wavelet analysis and support vector machine on weld surface images

Online monitoring of friction stir welding (FSW) is inevitable due to the increasing demand of this process. Also the machine vision system has industrial importance for monitoring of manufacturing processes due to its non-invasiveness and flexibility. Therefore, in this research, an attempt has been made to monitor friction stir welding process by analyzing the weld surface images. Here, discrete wavelet transform has been applied on FSW images to extract useful features for describing the good and defective weld. These obtained features have been fed to support vector machine based classification model for classifying good and defective weld with 99% and 97% accuracy with Gaussian and polynomial kernel, respectively.

Semantically Effective Visual Concept Illustration for Images

The field of analyzing and understanding high-dimension real world data in a knowledgeable form is known as computer vision. Image is such a high dimension real world data which is enormously available in meaningless way. Using Ontologies in this computer vision field will enable a high end Ontology knowledge based image analysis and understanding. The main objective of this paper is to develop a frame work that creates a Bag of Visual Words for sports events using low level features of images and to develop ontology to provide semantic meaning to the images. Such semantically available images can be easily retrieved using a semantic image retrieval system. We used the concepts of enhanced Scale Invariant Feature Transform (SIFT) for feature extraction and Support Vector Machine based classification model to provide semantic to the images for action classification of images