Cross-validated Support Vector Machine Research Articles

Concurrent inflammation-related brain reorganization in multiple sclerosis and depression

BackgroundNeuroinflammation affects brain tissue integrity in multiple sclerosis (MS) and may have a role in major depressive disorder (MDD). Whether advanced magnetic resonance imaging characteristics of the gray-to-white matter border serve as proxy of neuroinflammatory activity in MDD and MS remain unknown. MethodsWe included 684 participants (132 MDD patients with recurrent depressive episodes (RDE), 70 MDD patients with a single depressive episode (SDE), 222 MS patients without depressive symptoms (nMS), 58 MS patients with depressive symptoms (dMS), and 202 healthy controls (HC)). 3 T-T1w MRI-derived gray-to-white matter contrast (GWc) was used to reconstruct and characterize connectivity alterations of GWc-covariance networks by means of modularity, clustering coefficient, and degree. A cross-validated support vector machine was used to test the ability of GWc to stratify groups according to their depression symptoms, measured with BDI, at the single-subject level in MS and MDD independently. FindingsMS and MDD patients showed increased modularity (ANOVA partial-η2 = 0.3) and clustering (partial-η2 = 0.1) compared to HC. In the subgroups, a linear trend analysis attested a gradient of modularity increases in the form: HC, dMS, nMS, SDE, and RDE (ANOVA partial-η2 = 0.28, p < 0.001) while this trend was less evident for clustering coefficient. Reduced morphological integrity (GWc) was seen in patients with increased depressive symptoms (partial-η2 = 0.42, P < 0.001) and was associated with depression scores across patient groups (r = -0.2, P < 0.001). Depressive symptoms in MS were robustly classified (88 %). ConclusionsSimilar structural network alterations in MDD and MS exist, suggesting possible common inflammatory events like demyelination, neuroinflammation that are caught by GWc analyses. These alterations may vary depending on the severity of symptoms and in the case of MS may elucidate the occurrence of comorbid depression.

Differential Brain Activation for Four Emotions in VR-2D and VR-3D Modes.

Similar to traditional imaging, virtual reality (VR) imagery encompasses nonstereoscopic (VR-2D) and stereoscopic (VR-3D) modes. Currently, Russell's emotional model has been extensively studied in traditional 2D and VR-3D modes, but there is limited comparative research between VR-2D and VR-3D modes. In this study, we investigate whether Russell's emotional model exhibits stronger brain activation states in VR-3D mode compared to VR-2D mode. By designing an experiment covering four emotional categories (high arousal-high pleasure (HAHV), high arousal-low pleasure (HALV), low arousal-low pleasure (LALV), and low arousal-high pleasure (LAHV)), EEG signals were collected from 30 healthy undergraduate and graduate students while watching videos in both VR modes. Initially, power spectral density (PSD) computations revealed distinct brain activation patterns in different emotional states across the two modes, with VR-3D videos inducing significantly higher brainwave energy, primarily in the frontal, temporal, and occipital regions. Subsequently, Differential entropy (DE) feature sets, selected via a dual ten-fold cross-validation Support Vector Machine (SVM) classifier, demonstrate satisfactory classification accuracy, particularly superior in the VR-3D mode. The paper subsequently presents a deep learning-based EEG emotion recognition framework, adeptly utilizing the frequency, spatial, and temporal information of EEG data to improve recognition accuracy. The contribution of each individual feature to the prediction probabilities is discussed through machine-learning interpretability based on Shapley values. The study reveals notable differences in brain activation states for identical emotions between the two modes, with VR-3D mode showing more pronounced activation.

Machine Learning-Based Backpressure Unstart Prediction and Warning Method for Combined Cycle Engine Hypersonic Inlet-Oriented Wide Speed Range

Inlet unstart prediction and warning are strictly crucial to the operation of hypersonic engines, especially for combined cycle engines where implementation across a wide speed range poses significant challenges. This paper proposes a realization method that involves constructing the conditions of critical backpressure ratios for the inlet unstart and unstart warning states within a wide speed range and establishing the backpressure prediction models for each engine mode. The detection of the unstart and unstart warning states is achieved by predicting the backpressure ratio at the exit of the isolator and comparing it to the critical backpressure ratios. To achieve this, numerical simulations for a three-dimensional inward-turning multiducted hypersonic combined inlet at various Mach numbers and backpressure ratios are carried out to obtain the dataset of surface pressure. A 10-fold cross-validation support vector machine (10-CV SVM) is used to solve the unstart boundary of surface pressure, and an unstart margin is set to determine the unstart warning boundary. A back propagation (BP) neural network is constructed to estimate the critical backpressure ratios at each working point within a wide speed range. The data information of surface pressure on the boundaries is used as the input for the predictions. The overall average regression correlation coefficient approaches 0.99 on the test dataset at each working point. The backpressure prediction models are established by the one-dimensional convolutional neural network (1D-CNN). Only 2 to 4 measurement points of surface pressure are considered for cross-validation evaluation, and the mean absolute percentage error is between 4% and 8% with the average prediction time not exceeding 2 ms. Finally, the proposed method and prediction models are validated by wind tunnel experimental data.

Research on Fault Diagnosis of HVAC Systems Based on the ReliefF-RFECV-SVM Combined Model

A fault diagnosis method of heating, ventilation, and air conditioning (HVAC) systems based on the ReliefF-recursive feature elimination based on cross validation-support vector machine (ReliefF-RFECV-SVM) combined model is proposed to enhance the diagnosis accuracy and efficiency. The method initially uses ReliefF to screen the original features, selecting those that account for 95% of the total weight. The recursive feature elimination based on cross validation (RFECV), based on a random forest classifier, is then applied to select the optimal feature subset according to diagnostic accuracy. Finally, a support vector machine (SVM) model is constructed for fault classification. The method is tested on seven typical faults of the ASHRAE 1043-RP water chiller dataset and three typical faults of an air-cooled self-built air conditioner simulation dataset. The results show that the ReliefF-RFECV-SVM method significantly reduces diagnosis time compared to SVM, shortening it by about 50% based on the ASHRAE 1043-RP dataset, while achieving an overall accuracy of 99.98%. Moreover, the proposed method achieves a comprehensive diagnosis accuracy of 99.97% on the self-built simulation dataset, with diagnosis time the reduced by about 65% compared to single SVM.

Comparing Logistic Regression and Support Vector Machine in Breast Cancer Problem

There are several methods used for the classification problems. There are many different kinds of fields that can be used. Nowadays, Support Vector Machine (SVM) is a popular classification method that has been proposed by many researchers. Using the same method but different distribution methods for creating training and testing data in the same dataset can yield varying results in terms of prediction accuracy, which is crucial in classification. In this paper, we compare the prediction accuracy between SVM results and Logistic Regression results to determine the better method to classify the current condition of the patient after undergoing some treatment. Several treatments are used in this paper, including feature selection, feature extraction, separating the train and testing data using Holdout and K-Fold CV. Stepwise selection is done to reduce the features. Training and testing dataset is obtained using the five stratified and non-stratified holdout and five fold stratified and non-stratified cross validation. The result shows that the best method to classify the cancer dataset is five fold stratified cross validation SVM with radial kernel. The obtained accuracy is 81,816% with variance as much as 0,94%.

Fast Optical Signals for Real-Time Retinotopy and Brain Computer Interface.

A brain-computer interface (BCI) allows users to control external devices through brain activity. Portable neuroimaging techniques, such as near-infrared (NIR) imaging, are suitable for this goal. NIR imaging has been used to measure rapid changes in brain optical properties associated with neuronal activation, namely fast optical signals (FOS) with good spatiotemporal resolution. However, FOS have a low signal-to-noise ratio, limiting their BCI application. Here FOS were acquired with a frequency-domain optical system from the visual cortex during visual stimulation consisting of a rotating checkerboard wedge, flickering at 5 Hz. We used measures of photon count (Direct Current, DC light intensity) and time of flight (phase) at two NIR wavelengths (690 nm and 830 nm) combined with a machine learning approach for fast estimation of visual-field quadrant stimulation. The input features of a cross-validated support vector machine classifier were computed as the average modulus of the wavelet coherence between each channel and the average response among all channels in 512 ms time windows. An above chance performance was obtained when differentiating visual stimulation quadrants (left vs. right or top vs. bottom) with the best classification accuracy of ~63% (information transfer rate of ~6 bits/min) when classifying the superior and inferior stimulation quadrants using DC at 830 nm. The method is the first attempt to provide generalizable retinotopy classification relying on FOS, paving the way for the use of FOS in real-time BCI.

Random embedded calibrated statistical blind steganalysis using cross validated support vector machine and support vector machine with particle swarm optimization

The evolvement in digital media and information technology over the past decades have purveyed the internet to be an effectual medium for the exchange of data and communication. With the advent of technology, the data has become susceptible to mismanagement and exploitation. This led to the emergence of Internet Security frameworks like Information hiding and detection. Examples of domains of Information hiding and detection are Steganography and steganalysis respectively. This work focus on addressing possible security breaches using Internet security framework like Information hiding and techniques to identify the presence of a breach. The work involves the use of Blind steganalysis technique with the concept of Machine Learning incorporated into it. The work is done using the Joint Photographic Expert Group (JPEG) format because of its wide use for transmission over the Internet. Stego (embedded) images are created for evaluation by randomly embedding a text message into the image. The concept of calibration is used to retrieve an estimate of the cover (clean) image for analysis. The embedding is done with four different steganographic schemes in both spatial and transform domain namely LSB Matching and LSB Replacement, Pixel Value Differencing and F5. After the embedding of data with random percentages, the first order, the second order, the extended Discrete Cosine Transform (DCT) and Markov features are extracted for steganalysis.The above features are a combination of interblock and intra block dependencies. They had been considered in this paper to eliminate the drawback of each one of them, if considered separately. Dimensionality reduction is applied to the features using Principal Component Analysis (PCA). Block based technique had been used in the images for better accuracy of results. The technique of machine learning is added by using classifiers to differentiate the stego image from a cover image. A comparative study had been during with the classifier names Support Vector Machine and its evolutionary counterpart using Particle Swarm Optimization. The idea of cross validation had also been used in this work for better accuracy of results. Further parameters used in the process are the four different types of sampling namely linear, shuffled, stratified and automatic and the six different kernels used in classification specifically dot, multi-quadratic, epanechnikov, radial and ANOVA to identify what combination would yield a better result.

Fourier-transform near-infrared spectroscopy as a fast screening tool for the verification of the geographical origin of grain maize (Zea mays L.)

In this study, the ability of Fourier-transform near-infrared (FT-NIR) spectroscopy to trace back the geographical origin of grain maize used as feed material was investigated. 101 milled grain maize samples from five different countries (Spain, Ukraine, Slovakia, Peru and the USA) and three continents were analysed by FT-NIR spectroscopy. The spectra were used to develop a repeated cross-validated support vector machine classification, optimised in terms of pre-processing, model parameters and wavenumber selection. Spectral regions associated with proteins, starches and lipids were identified as suitable for determining the geographical origin of grain maize. A country-specific model composed of these selected regions achieved a mean accuracy rate of 95% for all samples. A similar overall result for country of origin classification was observed within a two-step approach starting with the continent level and then continuing with the country level within a continent. However, when differentiating between the geographical origins USA, Peru and Europe, all samples could be correctly classified. These results show the high potential of FT-NIR spectroscopy as a fast and cost-effective screening method for continent- and country of origin verification of grain maize samples in the context of feed authentication. • 101 milled grain maize samples were analysed by FT-NIR spectroscopy. • Spectral regions were identified that differ based on the geographical origin. • The geographical origin was verified using support vector machines. • The samples could be classified at the country of origin level with an accuracy of 95%. • No misclassification was observed on the continent level.

Optimization of matched filters for VHR image segmentation

ABSTRACT The availability of very high resolution remotely sensed images has made the use of spectral information alone insufficient for class recognition, so the integration of spatial information into the segmentation task becomes necessary. Spatial information takes into account the surrounding of a pixel, rather than dealing with a pixel as an isolated item. In this paper, inspired by matched filtering theory, we propose a new technique for spatial feature extraction. The technique consists of using 2D kernels convolved with the spectral bands. The convolution operation bears valuable spatial information about the pixel under consideration. The concatenation of the extracted spatial features and spectral features of pixels feeds a support vector machine (SVM) to segment the image of interest. To cope with the complexity of images having objects of varying sizes (i.e. urban areas), we adopted a hierarchical strategy. That is, kernels with increasing size are applied to extract different spatial features corresponding to different objects. Thus, we have extended the use of matched filters from single object enhancement to multi-object enhancement. A challenging step in designing the matched filters is the two-dimensional kernels coefficients selection, which we formulated as an optimization problem within a particle swarm optimization framework. The optimization process was driven by two different fitness functions, the cross-validation SVM accuracy and the Bhattacharyya distance, which were both evaluated on training samples. We assessed the proposed procedure on two very high-resolution images having different spatial resolutions. The obtained results showed significant improvement in terms of the overall classification accuracy (over 10% for both images). Moreover, visual inspection of the segmented images, in addition to pepper and salt elimination, revealed significant improvement in many objects not detected by the spectral method. Our method of extracting spatial features seems to be very efficient.

An Integrated Model of Atom Search Optimization-Based Resonance Sparse Signal Decomposition and Cross-Validation SVM for Gearbox Fault Diagnosis

In the aspect of gearbox fault diagnosis, the periodic pulse signal containing fault characteristics is often overwhelmed with other strong interference components, which brings a great challenge for gearbox fault detection and status identification. To address these issues, this paper develops a novel resonance-based sparse signal decomposition (RSSD) fault diagnosis method combined with support vector machine (SVM). Based on the key of the decomposition parameters in the resonant sparse decomposition method, the influence of atom search optimization (ASO) on the quality factor in the resonance-based sparse signal decomposition method is primarily studied. The vibration signal of the gearbox was decomposed by resonance sparse decomposition with the optimal quality factor, from which the high and low-resonance components were obtained. Then, the power spectrum entropy, singular spectrum entropy, and time-domain energy entropy of the low-resonance signal were calculated. Finally, the pattern recognition of gearbox fault was completed with a designed cross-validation SVM pattern recognition model. The numerical simulation and gearbox fault experiments demonstrate that the presented method can achieve great recognition accuracies and effect capacities against interference components involved in the gearbox vibration signal.

Distinct Features of Cerebral Blood Flow and Spontaneous Neural Activity as Integrated Predictors of Early Response to Antidepressants.

AimsThe purpose of this study is to explore whether pre-treatment features of brain function can discriminate non-responders to antidepressant medication in the early phase.MethodsForty-four treatment-responsive depressed (RD) patients, 36 non-responsive depressed (NRD) patients, and 42 healthy controls (HCs) were recruited. Regional cerebral blood flow (CBF) and amplitude of low-frequency fluctuation (ALFF) values were calculated for all subjects. Correlation analyses were used to explore the relationship between symptom improvement and CBF/ALFF. Receiver operating characteristics (ROC) and the 10-fold cross-validation support vector machine (SVM) classifier were applied for the discrimination of treatment response.ResultsCompared with the HCs, the RD and NRD groups exhibited lower CBF and ALFF in the right posterior lobe of the cerebellum. Compared with the NRD group, the RD group showed distinct CBF patterns in the left frontal striatal regions and right frontal cerebellar regions, as well as distinct ALFF features in the left frontoparietal striatum and right frontotemporal striatal cerebellar regions. The ROC and SVM classifier revealed the optimal power to distinguish the RD and NRD groups based on the combined measures (i.e., CBF and ALFF).ConclusionDistinct features of CBF and ALFF in the frontal striatal network may serve as promising neuroimaging predictors for identifying patients with blunted responsiveness, which may facilitate personalized antidepressant treatment.

Machine learning analysis of metabolomic biomarkers for diagnosis of heart failure

Abstract Background There is emerging evidence that the pathophysiological mechanisms of heart failure are associated with alterations in serum metabolites. Such metabolomic signatures may be useful for heart failure diagnosis, stratification and prognosis. Purpose To evaluate the utility of including metabolomic biomarkers in addition to traditional cardiac biomarkers in a machine learning prediction model of heart failure diagnosis in the well-characterised Canagliflozin Cardiovascular Assessment Study (CANVAS) cohort. Methods A subgroup of the CANVAS/CANVAS-R study cohort was analysed. 101 metabolites in plasma were measured by HPLC (HILIC)-mass spectrometry. A 10-times 5-fold cross-validated support vector machine model with radial basis kernel function was constructed to predict heart failure diagnosis using traditional biomarkers alone and using the combination of traditional biomarkers and metabolomic biomarkers. Model performance and variable importance were both evaluated by area under the curve (AUC) of the receiver operating characteristics (ROC) curve. Results are shown as mean ± standard deviation. Results 967 patients (of which 402 patients had heart failure) were included in the analysis with 341 females, mean age 63±8 years and mean body mass index (BMI) 33±5 kg/m2. All patients had diabetes mellitus with mean HbA1c 8.2±0.9%. The prediction model based on only traditional biomarkers had mean AUC 72±3% and the prediction model based on both traditional biomarkers and metabolomic biomarkers had mean AUC 80±3%. The top metabolomic biomarkers for predicting heart failure were threonine, L-homoserine, creatine and deoxyadenosine. Conclusion Metabolomic biomarkers improved diagnostic performance of a heart failure prediction model and captured variation not encompassed by traditional cardiac biomarkers. Funding Acknowledgement Type of funding sources: Private company. Main funding source(s): Janssen Research and Development

Research on the application of artificial intelligence method in automobile engine fault diagnosis

The application of artificial intelligence methods in fault diagnosis is becoming more and more extensive, and exploring and researching intelligent fault diagnosis methods for automobile engines is also a hot spot in the field of automotive engineering. Different machine learning methods have their own advantages and disadvantages. By extracting different characteristic parameters and optimizing the combination of multiple algorithms, faster and stable diagnosis results can be achieved, so that faults can be discovered and repaired in time. Aiming at the potential fluctuation and impact characteristics of vibration plus signal caused by different failure states of automobile engines, this paper proposes two engine fault identification methods using vibration acceleration signals as diagnostic parameters. They are Cross Validation -Support Vector Machine (CV-SVM)and Particle Swarm Optimization-Probabilistic Neural Network (PSO-PNN) engine fault identification methods. The advantages and disadvantages of the two methods are compared and analyzed. Obtain the amplitude corresponding to the frequency multiplication of the vibration acceleration signal through the spectrum analysis method, which is used as the main component of the input feature vector, and establish the SVM fault diagnosis model combined with the cross-validation method (CV); In addition, multiple one-dimensional arrays composed of time-domain signals are directly used as input feature vectors, and the particle swarm optimization (PSO) parameter optimization is used to obtain the best Probabilistic Neural Network(PNN) fault diagnosis model. The results show that both the CV-SVM (small sample) method and the PSO-PNN method (large sample) can realize the identification and diagnosis of the established engine fault type. The CV-SVM method has more advantages in diagnostic fault tolerance, but the PSO-PNN method can simplify the process of feature sample preparation, save a lot of manual feature extraction tasks, and is more convenient in practical application.

Individual prediction of trauma-focused psychotherapy response in youth with posttraumatic stress disorder using resting-state functional connectivity

Randomized controlled trials have shown efficacy of trauma-focused psychotherapies in youth with posttraumatic stress disorder (PTSD). However, response varies considerably among individuals. Currently, no biomarkers are available to assist clinicians in identifying youth who are most likely to benefit from treatment. In this study, we investigated whether resting-state functional magnetic resonance imaging (rs-fMRI) could distinguish between responders and non-responders on the group- and individual patient level. Pre-treatment rs-fMRI was recorded in 40 youth (ages 8–17 years) with (partial) PTSD before trauma-focused psychotherapy. Change in symptom severity from pre- to post-treatment was assessed using the Clinician-Administered PTSD scale for Children and Adolescents to divide participants into responders (≥30% symptom reduction) and non-responders. Functional networks were identified using meta-independent component analysis. Group-differences within- and between-network connectivity between responders and non-responders were tested using permutation testing. Individual predictions were made using multivariate, cross-validated support vector machine classification. A network centered on the bilateral superior temporal gyrus predicted treatment response for individual patients with 76% accuracy (pFWE = 0.02, 87% sensitivity, 65% specificity, area-under-receiver-operator-curve of 0.82). Functional connectivity between the frontoparietal and sensorimotor network was significantly stronger in non-responders (t = 5.35, pFWE = 0.01) on the group-level. Within-network connectivity was not significantly different between groups. This study provides proof-of-concept evidence for the feasibility to predict trauma-focused psychotherapy response in youth with PTSD at an individual-level. Future studies are required to test if larger cohorts could increase accuracy and to test further generalizability of the prediction models.

NIMG-22. INTEGRATION OF A RADIOMIC SIGNATURE, CLINICAL VARIABLES AND PLASMA CELL-FREE DNA IN ADULT PATIENTS WITH NEWLY DIAGNOSED GLIOBLASTOMA PREDICTS PATIENT SURVIVAL AND IMPROVES DISEASE STRATIFICATION

Abstract PURPOSE We have previously demonstrated the potential role of liquid biopsy, specifically plasma cell-free DNA (cfDNA), as a non-invasive biomarker for prognostication in patients with glioblastoma. In separate prior studies, we have also developed MRI-based radiomic signatures to predict survival outcomes in glioblastoma. In this study, for the first time, we evaluated the potential of combining radiomic signatures, epidemiological and clinical variables, and plasma cfDNA quantification for upfront prediction of overall survival (OS) in patients with newly diagnosed glioblastoma. METHODS Quantitative radiomic features were extracted from multiparametric MRI (T1, T1Gd, T2, T2-FLAIR) scans of a discovery cohort of 505 and an independent replication cohort of 50 IDH-wildtype glioblastoma patients. For the independent replication cohort, pre-surgical plasma cfDNA was extracted and quantified. In the first stage, a radiomic signature was created for stratification of patients into categories of short (OS ≤ 6 months) and long (OS ≥ 18 months) survivors using a cross-validated XGBoost method based on the discovery cohort, which was tested independently on the replication cohort. In the second stage, the radiomic signature and clinical variables were integrated to build a second-stage signature using a cross-validated support vector machine (SVM) classifier to stratify the patients into short and long survivor categories. In the third stage, the value of the second-stage signature integrated with cfDNA concentration was assessed through a cross-validated SVM regression method. RESULTS The combination of radiomic, clinical, and cfDNA variables resulted in the best overall predictive accuracy, with Pearson’s correlation coefficient of 0.59 (p&amp;lt; 0.0001) between actual and predicted OS. CONCLUSION In this study, we evaluated the value of combining plasma cfDNA, radiomic, and clinical variables for predicting OS, and showed that it could act as an effective non-invasive prognostic and patient stratification tool in patients with newly diagnosed glioblastoma.

Changes in functional connectivity after theta-burst transcranial magnetic stimulation for post-traumatic stress disorder: a machine-learning study

Intermittent theta burst stimulation (iTBS) is a novel treatment approach for post-traumatic stress disorder (PTSD), and recent neuroimaging work indicates that functional connectivity profiles may be able to identify those most likely to respond. However, prior work has relied on functional magnetic resonance imaging, which is expensive and difficult to scale. Alternatively, electroencephalography (EEG) represents a different approach that may be easier to implement in clinical practice. To this end, we acquired an 8-channel resting-state EEG signal on participants before (n = 47) and after (n = 43) randomized controlled trial of iTBS for PTSD (ten sessions, delivered at 80% of motor threshold, 1,800 pulses, to the right dorsolateral prefrontal cortex). We used a cross-validated support vector machine (SVM) to track changes in EEG functional connectivity after verum iTBS stimulation. We found that an SVM classifier was able to successfully separate patients who received active treatment vs. sham treatment, with statistically significant findings in the Delta band (1–4 Hz, p = 0.002). Using Delta coherence, the classifier was 75.0% accurate in detecting sham vs. active iTBS, and observed changes represented an increase in functional connectivity between midline central/occipital and a decrease between frontal and central regions. The primary limitations of this work are the sparse electrode system and a modest sample size. Our findings raise the possibility that EEG and machine learning may be combined to provide a window into mechanisms of action of TMS, with the potential that these approaches can inform the development of individualized treatment methods.

The performance of intravoxel-incoherent motion diffusion-weighted imaging derived hypoxia for the risk stratification of prostate cancer in peripheral zone

PurposeTo assess the association between intravoxel-incoherent motion diffusion-weighted imaging (IVIM) derived hypoxia and the aggressiveness of prostate cancer (PCa) and to explore its contribution to the risk stratification of PCa. MethodsSeventy-five peripheral zone (PZ) PCa patients, who underwent multiparametric MRI (mpMRI), were included in this study. Systematic ultrasound guided biopsy was used as reference. IVIM was acquired with 5 b values (b = 0∼750 s/mm2). Apparent diffusion coefficient (ADC), pure tissue diffusion (Ds), volume fraction of pseudo-diffusion (fp), hypoxic fraction (HFDWI), hypoxia score (HSDWI) and relative oxygen saturation(rOSDWI), were calculated and histogram analysis was applied. Groups comparison was performed between low-intermediate-grade group (LG, the International Society of Urological Pathology (ISUP) Gleason Grade (GG) ≤2) and high-grade (HG, ISUP GG ≥ 3) group. The correlation between diffusion parameters and ISUP GG was assessed. Cross-validated Support Vector Machine (SVM) Classification was performed and compared with univariate ROC analysis to explore the risk stratification of PZ PCa. ResultsMean, median, and the 10th percentile of Ds differed significantly between groups (p < 0.05). Several parameters significantly correlated with ISUP grade, and the 10th percentile of Ds showed the strongest correlation (ρ= − 0.284). The prediction model containing IVIM derived hypoxia yielded an area under the receiver operating characteristics curve (AUC) ranging 0.749–0.786 for cross-validation. The AUCs of the SVM modeling were higher than that of any single parameter. ConclusionIVIM derived hypoxia demonstrated significant correlation with the aggressiveness of PCa. It’s supplemental to the MRI assessment of PCa with a promising stratification of risk stratification of PZ PCa.

Penggunaan Feature Selection di Algoritma Support Vector Machine untuk Sentimen Analisis Komisi Pemilihan Umum

At this time sentiment analysis is very widely used by people to see the extent of people's sentiments towards an object. Objects that can be used in sentiment analysis can be various kinds, for example about the product regarding receipt by consumers, agencies or institutions regarding the performance of the agency. Whereas for this study taking sentiment analysis of the State Institution namely the General Election Commission (KPU) about the sentiments of the implementation of the ELECTION simultaneously and also the results of the implementation of the ELECTION which have become the subject of discussion by netizens on social media. So this research takes retweet data and retention comments from Twitter social media users. The algorithm used in this study is Support Vector Machine (SVM), with optimization of the use of Weight by Correlation Feature Selection (FS). The results of cross validation SVM without FS are 66.49% for accuracy and 0.716 for AUC. Whereas SVM with FS is 81.18% for accuracy and 0.943 for AUC. Very significant improvement with the use of Weight by Correlation Feature Selection (FS).

NIMG-35. QUANTITATIVE ESTIMATION OF PROGRESSION-FREE SURVIVAL BASED ON RADIOMICS ANALYSIS OF PREOPERATIVE MULTI-PARAMETRIC MRI IN PATIENTS WITH GLIOBLASTOMA

Abstract PURPOSE Glioblastoma managed with maximal resection and adjuvant chemoradiation has large heterogeneity at the time of tumor recurrence (progression-free survival, PFS). Upfront identification of patients with shorter than median PFS, may facilitate better personalization of treatment, such as patient stratification into clinical trials for treatment intensification and/or supportive care. The aim of the current study was to build a radiomics model that can reliably predict PFS in patients with glioblastoma at the time of initial diagnosis. EXPERIMENTAL DESIGN: A total of 66 de novo glioblastoma patients in a single institution who underwent gross total resection followed by standard adjuvant chemoradiation, were found to have pathologically confirmed recurrence. Patients who had sufficient follow-up MRI to reliably determine PFS and available pre-surgical multi-parametric MRI (mpMRI) (T1, T1Gd, T2, T2-FLAIR, DTI, DSC-MR images) were included. The patients were stratified into two classes of “short PFS (≤7 months, n=35)” and “long PFS (≥9 months, n=19)”. An extensive set of features was extracted from preoperative mpMRI scans, including shape and volumetric measures computed for different tumorous regions, and characteristics derived from histograms and gray-level co-occurrence matrix (GLCM). Predictive modeling for discrimination of patients with short from those with long PFS was performed using a 10-fold cross-validated support vector machine classifier. RESULTS An accuracy of 79.6% was achieved for prediction of short and long PFS (sensitivity=83%, specificity=74%, AUC=0.86 [95%CI: 0.76–0.96]; short-PSF was considered the positive class). The patients with shorter PFS showed markedly higher cell density in the nonenhancing tumor (DTI), higher neo-angiogenesis in the enhancing tumor (DSC-MRI, T1Gd), lower water concentration in the enhancing tumor region (T2), and higher maximum enhancement (calculated by the subtraction of T1 from T1Gd) in the edema region. CONCLUSION Quantitative assessment of preoperative mpMRI provides accurate prediction of PFS for patients with glioblastoma, which can aid in personalized treatment planning.

Recognition of Weld Penetration During K-TIG Welding Based on Acoustic and Visual Sensing

In the field of welding process control, on-line monitoring of welding quality based on multi-sensor information fusion has attracted more attention. In order to recognize the penetration state of the Keyhole mode Tungsten Inert Gas welded joint in real time, an acoustic and visual sensing system was established in this paper. The acoustic and visual features that characterize the penetration state of the welded joints in 34 dimensions were extracted and the variation of the acoustic signal and the keyhole geometry were analyzed. In addition, the weighted scoring criterion based on the Fisher distance and the maximum information coefficient (Fisher–MIC) and Support Vector Machine (SVM) model based on cross-validation (CV) are designed as the feature selection method. The feature selection method can evaluate the penetration recognition accuracy of different feature subsets. The experiment results show that the maximum recognition accuracy was 97.1655%, which was performed by the 10-dimension optimal feature subset and the CV–SVM model with particle swarm optimization (PSO–CV–SVM). It is proved that the selected acoustic and visual features can well characterize the penetration state of the welded joints, and the feature selection method and PSO–CV–SVM model have superior performance.