Multivariate Support Vector Regression Research Articles

System-level performance prognosis based on data augmentation for air brake systems of in-service trains

In order to prognose the performance for air brake systems of in-service trains, a data augmentation method based on correlation analysis and improved multivariate support vector regression was proposed in this paper. By using black box theory and correlation analysis, brake cylinder pressure was extracted as the performance identification signal of air brake system, and the input and output signals were used as the auxiliary signals to construct the black box model of air brake system. Meanwhile, in order to make full use of the obtained data information, a data augmentation prognosis model based on improved multivariate support vector regression was established. Moreover, the optimal parameters of prognosis model were selected by means of particle swarm optimization algorithm, and RMSE and MAE were used as evaluation indicators. Finally, case studies on test-rig performance experiment data of air brake system were conducted. The prognosis model was trained and verified by using the service 1-7N and emergency, service full brake-relief and stage brake-relief experiment data, respectively, and the modeling and calibration error at pressure-holding stage were both in the order of ±5 kPa, which demonstrated the proposed method to be quite accurate and effective.

Multivariate SVR Demand Forecasting for Beauty Products Based on Online Reviews

Owing to changes in consumer attitudes, the beauty consumer population is growing rapidly and the demands of beauty consumers are variable. With a wide range of beauty products and exaggerated product promotions, consumers rely more on online reviews to perceive product information. In this paper, we propose a demand forecasting model that takes into account both product features and product emotional needs based on online reviews to help companies better develop production and sales plans. Firstly, a Word2vec model and sentiment analysis method based on a sentiment dictionary are used to extract product features and factors influencing product sentiment; secondly, a multivariate Support Vector Regression (SVR) demand prediction model is constructed and the model parameters are optimized using particle swarm optimization; and finally, an example analysis is conducted with beauty product Z. The results show that compared with the univariate SVR model and the multivariate SVR model with only product feature demand as the influencing factor, the multivariate SVR model with both product feature and product sentiment demand as influencing factors has a smaller prediction error, which can enable beauty retail enterprises to better grasp consumer demand dynamics, make flexible production and sales plans, and effectively reduce production costs.

Decreased functional concordance in male children with autism spectrum disorder.

Autism spectrum disorder (ASD) is an early-onset neurodevelopmental condition with altered function of the brain. At present, a variety of functional metrics from neuroimaging techniques have been used to explore ASD neurological mechanisms. However, the concordance of these functional metrics in ASD is still unclear. This study used resting-state functional magnetic resonance imaging data, which were obtained from the open-access Autism Brain Imaging Data Exchange database, including 105 children with ASD and 102 demographically matched typically developing (TD) children. Both voxel-wise and volume-wise functional concordance were calculated by combining the dynamic amplitude of low-frequency fluctuations, dynamic regional homogeneity, and dynamic global signal correlation. Furthermore, a two-sample t-test was performed to compare the functional concordance between ASD and TD groups. Finally, the relationship between voxel-wise functional concordance and Autism Diagnostic Observation Schedule subscores was analyzed using the multivariate support vector regression in the ASD group. Compared with the TD group, we found that ASD showed decreased voxel-wise functional concordance in the left superior temporal pole (STGp), right amygdala, and left opercular part of the inferior frontal gyrus (IFGoper). Moreover, decreased functional concordance was associated with restricted and repetitive behaviors in ASD. Our results found altered brain function in the left STGp, right amygdala, and left IFGoper in ASD by functional concordance, indicating that functional concordance may provide new insights into the neurological mechanisms of ASD.

Neuroanatomy of post-stroke depression: the association between symptom clusters and lesion location.

Post-stroke depression affects about 30% of stroke patients and often hampers functional recovery. The diagnosis of depression encompasses heterogeneous symptoms at emotional, motivational, cognitive, behavioural or somatic levels. Evidence indicates that depression is caused by disruption of bio-aminergic fibre tracts between prefrontal and limbic or striatal brain regions comprising different functional networks. Voxel-based lesion-symptom mapping studies reported discrepant findings regarding the association between infarct locations and depression. Inconsistencies may be due to the usage of sum scores, thereby mixing different symptoms of depression. In this cross-sectional study, we used multivariate support vector regression for lesion-symptom mapping to identify regions significantly involved in distinct depressive symptom domains and global depression. MRI lesion data were included from 200 patients with acute first-ever ischaemic stroke (mean 0.9 ± 1.5 days of post-stroke). The Montgomery-Åsberg Depression Rating interview assessed depression severity in five symptom domains encompassing motivational, emotional and cognitive symptoms deficits, anxiety and somatic symptoms and was examined 8.4 days of post-stroke (±4.3). We found that global depression severity, irrespective of individual symptom domains, was primarily linked to right hemispheric lesions in the dorsolateral prefrontal cortex and inferior frontal gyrus. In contrast, when considering distinct symptom domains individually, the analyses yielded much more sensitive results in regions where the correlations with the global depression score yielded no effects. Accordingly, motivational deficits were associated with lesions in orbitofrontal cortex, dorsolateral prefrontal cortex, pre- and post-central gyri and basal ganglia, including putamen and pallidum. Lesions affecting the dorsal thalamus, anterior insula and somatosensory cortex were significantly associated with emotional symptoms such as sadness. Damage to the dorsolateral prefrontal cortex was associated with concentration deficits, cognitive symptoms of guilt and self-reproach. Furthermore, somatic symptoms, including loss of appetite and sleep disturbances, were linked to the insula, parietal operculum and amygdala lesions. Likewise, anxiety was associated with lesions impacting the central operculum, insula and inferior frontal gyrus. Interestingly, symptoms of anxiety were exclusively left hemispheric, whereas the lesion-symptom associations of the other domains were lateralized to the right hemisphere. In conclusion, this large-scale study shows that in acute stroke patients, differential post-stroke depression symptom domains are associated with specific structural correlates. Our findings extend existing concepts on the neural underpinnings of depressive symptoms, indicating that differential lesion patterns lead to distinct depressive symptoms in the first weeks of post-stroke. These findings may facilitate the development of personalized treatments to improve post-stroke rehabilitation.

Disconnectomics to unravel the network underlying deficits of spatial exploration and attention

Spatial attention and exploration are related to a predominantly right hemispheric network structure. However, the areas of the brain involved and their exact role is still debated. Spatial neglect following right hemispheric stroke lesions has been frequently viewed as a model to study these processes in humans. Previous investigations on the anatomical basis on spatial neglect predominantly focused on focal brain damage and lesion-behaviour mapping analyses. This approach might not be suited to detect remote areas structurally spared but which might contribute to the behavioural deficit. In the present study of a sample of 203 right hemispheric stroke patients, we combined connectome lesion-symptom mapping with multivariate support vector regression to unravel the complex and disconnected network structure in spatial neglect. We delineated three central nodes that were extensively disconnected from other intrahemispheric areas, namely the right superior parietal lobule, the insula, and the temporal pole. Additionally, the analysis allocated central roles within this network to the inferior frontal gyrus (pars triangularis and opercularis), right middle temporal gyrus, right temporal pole and left and right orbitofrontal cortices, including interhemispheric disconnection. Our results suggest that these structures—although not necessarily directly damaged—might play a role within the network underlying spatial neglect in humans.

424 The Role of the Mid Fusiform Gyrus in Lexical Retrieval

INTRODUCTION: Temporal lobe resections for epilepsy or neoplasms often result in significant confrontation naming decline. This can be socio-economically disabling and prevent patients from returning to independent functioning. While the exact substrates responsible are unknown, it was previously assumed that injury to the superior temporal gyrus or resection size predicts these declines. A clear understanding of the most critical constituents might influence surgical strategies to minimize language declines. METHODS: Data were obtained from 95 patients who underwent surgical resection in the dominant left temporal lobe for medication-resistant epilepsy. Patients underwent neuropsychological testing and MRI prior to and 6 months following surgery. Lesion masks were traced on postoperative MRIs and aligned to a normative space. The effects of preoperative scores and seizure outcomes were removed from postoperative scores via linear regression. VLSM using multivariate support vector regression was used to assess postoperative test scores. Beta maps were converted to p values and corrected using a permutation-based cluster level correction. Additionally, a surface-based mixed-effects multilevel analysis was used to estimate broadband gamma activity during picture naming across a subset of subjects with ECoG recordings, and results were integrated with VLSM. Lastly, fMRI (picture naming) was used to assess SNR in significant regions. RESULTS: VLSM analysis revealed that the loss of basal temporal regions was associated with a prominent decline in BNT scores (p < 0.005). Similarly, ECoG analysis showed a significant increase in activity in the mid fusiform gyrus (mFus) immediately preceding articulation. Many of these voxels were associated with low SNR on fMRI, perhaps explaining why this region has been under-appreciated as the locus responsible for postoperative deficits. CONCLUSION: The importance of the ventral temporal cortex in lexical access is shown using multivariate VLSM and supported with ECoG. While it has previously been assumed that mFus lesions do not cause pervasive impairment, our data and recent work (FATES study) argue against this and support the role of the mFus as a critical semantic access hub.

Decoding explicit and implicit representations of health and taste attributes of foods in the human brain

Obesity has become a significant problem word-wide and is strongly linked to poor food choices. Even in healthy individuals, taste perceptions often drive dietary decisions more strongly than healthiness. This study tested whether health and taste representations can be directly decoded from brain activity, both when explicitly considered, and when implicitly processed for decision-making. We used multivariate support vector regression for event-related potentials (as measured by the electroencephalogram) to estimate a regression model predicting ratings of tastiness and healthiness for each participant, based on their neural activity occurring in the first second of food cue processing. In Experiment 1, 37 healthy participants viewed images of various foods and explicitly rated their tastiness and healthiness. In Experiment 2, 89 healthy participants completed a similar rating task, followed by an additional experimental phase, in which they indicated their desire to consume snack foods with no explicit instruction to consider tastiness or healthiness. In Experiment 1 both attributes could be decoded, with taste information being available earlier than health. In Experiment 2, both dimensions were also decodable, and their significant decoding preceded the decoding of decisions (i.e., desire to consume the food). However, in Experiment 2, health representations were decodable earlier than taste representations. These results suggest that health information is activated in the brain during the early stages of dietary decisions, which is promising for designing obesity interventions aimed at quickly activating health awareness.

Strategic Infarct Locations for Poststroke Depressive Symptoms: A Lesion- and Disconnection-Symptom Mapping Study

BackgroundDepression is the most common neuropsychiatric complication after stroke. Infarct location is associated with poststroke depressive symptoms (PSDS), but it remains debated which brain structures are critically involved. We performed a large-scale lesion-symptom mapping study to identify infarct locations and white matter disconnections associated with PSDS. MethodsWe included 553 patients (mean [SD] age = 69 [11] years, 42% female) with acute ischemic stroke. PSDS were measured using the 30-item Geriatric Depression Scale. Multivariable support vector regression (SVR)–based analyses were performed both at the level of individual voxels (voxel-based lesion-symptom mapping) and at predefined regions of interest to relate infarct location to PSDS. We externally validated our findings in an independent stroke cohort (N = 459). Finally, disconnectome-based analyses were performed using SVR voxel-based lesion-symptom mapping, in which white matter fibers disconnected by the infarct were analyzed instead of the infarct itself. ResultsInfarcts in the right amygdala, right hippocampus, and right pallidum were consistently associated with PSDS (permutation-based p < .05) in SVR voxel-based lesion-symptom mapping and SVR region-of-interest analyses. External validation confirmed the association between infarcts in the right amygdala and pallidum, but not the right hippocampus, and PSDS. Disconnectome-based analyses revealed that disconnections in the right parahippocampal white matter, right thalamus and pallidum, and right anterior thalamic radiation were significantly associated (permutation-based p < .05) with PSDS. ConclusionsInfarcts in the right amygdala and pallidum and disconnections of right limbic and frontal cortico-basal ganglia-thalamic circuits are associated with PSDS. Our findings provide a comprehensive and integrative picture of strategic infarct locations for PSDS and shed new light on pathophysiological mechanisms of depression after stroke.

Domains of Health-Related Quality of Life Are Associated With Specific Deficits and Lesion Locations in Chronic Aphasia

Background Health-related quality of life (HRQL) in stroke survivors is related to numerous factors, but more research is needed to delineate factors related to HRQL in people with aphasia. Objective To examine the relationship between HRQL and demographic factors, impairment-based measures, and lesion characteristics in chronic aphasia. Methods A total of 41 left-hemisphere stroke survivors with aphasia underwent cognitive testing and magnetic resonance imaging. To address relationships with demographic and impairment-based measures, test scores were entered into a principal component analysis (PCA) and multiple linear regression was performed for overall and domain (physical, communication, psychosocial) scores of the Stroke and Aphasia Quality of Life Scale (SAQOL-39g). Independent variables included factor scores from the PCA, motricity, lesion volume, depressed mood, and demographic variables. To address relationships with lesion location, multivariate support vector regression lesion-symptom mapping (SVR-LSM) was used to localize lesions associated with SAQOL-39g scores. Results The PCA yielded 3 factors, which were labeled Language Production, Nonlinguistic Cognition, and Language Comprehension. Multiple linear regression revealed that depression symptoms predicted lower SAQOL-39g average and domain scores. Lower motricity scores predicted lower SAQOL-39g average and physical scores, and lower Language Production factor scores predicted lower communication scores. SVR-LSM demonstrated that basal ganglia lesions were associated with lower physical scores, and inferior frontal lesions were associated with lower psychosocial scores. Conclusions HRQL in chronic left-hemisphere stroke survivors with aphasia relates to lesion location, depression symptoms, and impairment-based measures. This information may help identify individuals at risk for specific aspects of low HRQL and facilitate targeted interventions to improve well-being.

Wind Turbine Operation Curves Modelling Techniques

Wind turbines are machines operating in non-stationary conditions and the power of a wind turbine depends non-trivially on environmental conditions and working parameters. For these reasons, wind turbine power monitoring is a complex task which is typically addressed through data-driven methods for constructing a normal behavior model. On these grounds, this study is devoted the analysis of meaningful operation curves, which are rotor speed-power, generator speed-power and blade pitch-power. A key point is that these curves are analyzed in the appropriate operation region of the wind turbines: the rotor and generator curves are considered for moderate wind speed, when the blade pitch is fixed and the rotational speed varies (Region 2); the blade pitch curve is considered for higher wind speed, when the rotational speed is rated (Region 2 12). The selected curves are studied through a multivariate Support Vector Regression with Gaussian Kernel on the Supervisory Control And Data Acquisition (SCADA) data of two wind farms sited in Italy, featuring in total 15 2 MW wind turbines. An innovative aspect of the selected models is that minimum, maximum and standard deviation of the independent variables of interest are fed as input to the models, in addition to the typically employed average values: using the additional covariates proposed in this work, the error metrics decrease of order of one third, with respect to what would be obtained by employing as regressors only the average values of the independent variables. In general it results that, for all the considered curves, the prediction of the power is characterized by error metrics which are competitive with the state of the art in the literature for multivariate wind turbine power curve analysis: in particular, for one test case, a mean absolute percentage error of order of 2.5% is achieved. Furthermore, the approach presented in this study provides a superior capability of interpreting wind turbine performance in terms of the behavior of the main sub-components and eliminates as much as possible the dependence on nacelle anemometer data, whose use is critical because of issues related to the sites complexity.

Neural patterns during anticipation predict emotion regulation success for reappraisal.

The ability to exert control over emotions, termed emotion regulation (ER), is vital for everyday functioning. ER success may be influenced by processes relating to the anticipation (prior to active regulation) and implementation (during active regulation) of ER strategy use. We investigated whether brain activity patterns recorded using electroencephalography (EEG) during the first second of anticipation and implementation of two ER strategies-distraction and reappraisal-were related to regulation success. Participants viewed negative images that evoked disgust and sadness. Before each image was presented, participants were cued to either passively view the image or decrease their emotional responses. ER success scores were calculated from subsequent self-reported disgust and sadness ratings. Using multivariate support vector regression, ER success scores were predicted from spatiotemporal patterns of event-related potentials during the first second of anticipation and implementation phases of each ER strategy. For both sadness and disgust, reappraisal success could be predicted during anticipation, while distraction success could be predicted during implementation. These findings suggest that early anticipatory cognitive processes are a key determinant of reappraisal success, but may not be similarly important for distraction. This may be because reappraisal is more cognitively demanding than distraction, requiring enhanced preparation of mental resources.

A Study of Wind Turbine Performance Decline with Age through Operation Data Analysis

Ageing of technical systems and machines is a matter of fact. It therefore does not come as a surprise that an energy conversion system such as a wind turbine, which in particular operates under non-stationary conditions, is subjected to performance decline with age. The present study presents an analysis of the performance deterioration with age of a Vestas V52 wind turbine, installed in 2005 at the Dundalk Institute of Technology campus in Ireland. The wind turbine has operated from October 2005 to October 2018 with its original gearbox, that has subsequently been replaced in 2019. Therefore, a key point of the present study is that operation data spanning over thirteen years have been analysed for estimating how the performance degrades in time. To this end, one of the most innovative approaches for wind turbine performance control and monitoring has been employed: a multivariate Support Vector Regression with Gaussian Kernel, whose target is the power output of the wind turbine. Once the model has been trained with a reference data set, the performance degradation is assessed by studying how the residuals between model estimates and measurements evolve. Furthermore, a power curve analysis through the binning method has been performed to estimate the Annual Energy Production variations and suggests that the most convenient strategy for the test case wind turbine (running the gearbox until its end of life) has indeed been adopted. Summarizing, the main results of the present study are as follows: over a ten-year period, the performance of the wind turbine has declined of the order of 5%; the performance deterioration seems to be nonlinear as years pass by; after the gearbox replacement, a fraction of performance deterioration has been recovered, though not all because the rest of the turbine system has been operating for thirteen years from its original state. Finally, it should be noted that the estimate of performance decline is basically consistent with the few results available in the literature.

A spatial multivariable SVR method for spatiotemporal fuzzy modeling with applications to rapid thermal processing

Many industrial processes have significant spatiotemporal dynamics and they are usually called distributed parameter systems (DPSs). Modeling such system is challenging due to its nonlinearity, time-varying dynamics, and spatiotemporal coupling. Using model reduction techniques, traditional DPS modeling methods usually reduce an infinite-dimensional system to a finite-dimensional system, which leads to unknown nonlinearity and unmodeled dynamics. The modeling method and the established model are hard to understand. Here, we propose a spatial multivariable support vector regression (SVR) based three-domain (3-D) fuzzy modeling method for complex nonlinear DPSs. The proposed 3-D modeling method integrates the time-space separation and time-space synthesis into a 3-D fuzzy model. Therefore, it does not require model reduction and owns the capability of linguistic interpretability. A spatial multivariable SVR with spatial kernel functions is proposed to deal with spatiotemporal data. The spatial fuzzy basis functions from a 3-D fuzzy model are spatial kernel functions for a spatial multivariable SVR, which satisfy Mercy theorem. Hence, the spatial multivariable SVR can be directly employed to build up a complete 3-D fuzzy rule-base of the 3-D fuzzy model. The proposed modeling method integrates the merits of learning ability from a spatial multivariable SVR and fuzzy space processing and fuzzy linguistic expression from a 3-D fuzzy model. The proposed 3-D fuzzy modeling method is successful applied to a simulated rapid thermal processing system. In comparison with several newly developed modeling methods for DPSs, the simulation results validate the superiority of the proposed modeling method.

Altruistic decisions following penetrating traumatic brain injury.

The cerebral correlates of altruistic decisions have increasingly attracted the interest of neuroscientists. To date, investigations on the neural underpinnings of altruistic decisions have primarily been conducted in healthy adults undergoing functional neuroimaging as they engaged in decisions to punish third parties. The chief purpose of the present study was to investigate altruistic decisions following focal brain damage with a novel altruistic decision task. In contrast to studies that have focused either on altruistic punishment or donation, the Altruistic Decision Task allows players to anonymously punish or donate to 30 charitable organizations involved with salient societal issues such as abortion, nuclear energy and civil rights. Ninety-four Vietnam War veterans with variable patterns of penetrating traumatic brain injury and 28 healthy veterans who also served in combat participated in the study as normal controls. Participants were asked to invest $1 to punish or reward real societal organizations, or keep the money for themselves. Associations between lesion distribution and performance on the task were analysed with multivariate support vector regression, which enables the assessment of the joint contribution of multiple regions in the determination of a given behaviour of interest. Our main findings were: (i) bilateral dorsomedial prefrontal lesions increased altruistic punishment, whereas lesions of the right perisylvian region and left temporo-insular cortex decreased punishment; (ii) altruistic donations were increased by bilateral lesions of the dorsomedial parietal cortex, whereas lesions of the right posterior superior temporal sulcus and middle temporal gyri decreased donations; (iii) altruistic punishment and donation were only weakly correlated, emphasizing their dissociable neuroanatomical associations; and (iv) altruistic decisions were not related to post-traumatic personality changes. These findings indicate that altruistic punishment and donation are determined by largely non-overlapping cerebral regions, which have previously been implicated in social cognition and moral experience such as evaluations of intentionality and intuitions of justice and morality.10.1093/brain/awy064_video1awy064media15758316955001.

Brain hubs in lesion models: Predicting functional network topology with lesion patterns in patients

Various important topological properties of healthy brain connectome have recently been identified. However, the manner in which brain lesion changes the functional network topology is unknown. We examined how critical specific brain areas are in the maintenance of network topology using multivariate support vector regression analysis on brain structural and resting-state functional imaging data in 96 patients with brain damages. Patients’ cortical lesion distribution patterns could significantly predict the functional network topology and a set of regions with significant weights in the prediction models were identified as “lesion hubs”. Intriguingly, we found two different types of lesion hubs, whose lesions associated with changes of network topology towards relatively different directions, being either more integrated (global) or more segregated (local), and correspond to hubs identified in healthy functional network in complex manners. Our results pose further important questions about the potential dynamics of the functional brain network after brain damage.

Intrinsic functional connectivity predicts individual differences in distractibility

Distractor suppression, the ability to filter and ignore task-irrelevant information, is critical for efficient task performance. While successful distractor suppression relies on a balance of activity in neural networks responsible for attention maintenance (dorsal attention network; DAN), reorientation (ventral attention network; VAN), and internal thought (default mode network, DMN), the degree to which intrinsic connectivity within and between these networks contributes to individual differences in distractor suppression ability is not well-characterized. For the purposes of understanding these interactions, the current study collected resting-state fMRI data from 32 Veterans and, several months later (7±5 months apart), performance on the additional singleton paradigm, a measure of distractor suppression. Using multivariate support vector regression models composed of resting state connectivity between regions of the DAN, VAN, and DMN, and a leave-one-subject-out cross-validation procedure, we were able to predict an individual's task performance, yielding a significant correlation between the actual and predicted distractor suppression (r=0.48, p=0.0053). Network-level analyses revealed that greater within-network DMN connectivity was predictive of better distractor suppression, while greater connectivity between the DMN and attention networks was predictive of poorer distractor suppression. The strongest connection hubs were determined to be the right frontal eye field and temporoparietal junction of the DAN and VAN, respectively, and medial (ventromedial prefrontal and posterior cingulate cortices) and bilateral prefrontal regions of the DMN. These results are amongst a small but growing number of studies demonstrating that resting state connectivity is related to stable individual differences in cognitive ability, and suggest that greater integrity and independence of the DMN is related to better attentional ability.

Distributed patterns of event-related potentials predict subsequent ratings of abstract stimulus attributes.

Exposure to pleasant and rewarding visual stimuli can bias people's choices towards either immediate or delayed gratification. We hypothesised that this phenomenon might be based on carry-over effects from a fast, unconscious assessment of the abstract ‘time reference’ of a stimuli, i.e. how the stimulus relates to one's personal understanding and connotation of time. Here we investigated whether participants' post-experiment ratings of task-irrelevant, positive background visual stimuli for the dimensions ‘arousal’ (used as a control condition) and ‘time reference’ were related to differences in single-channel event-related potentials (ERPs) and whether they could be predicted from spatio-temporal patterns of ERPs. Participants performed a demanding foreground choice-reaction task while on each trial one task-irrelevant image (depicting objects, people and scenes) was presented in the background. Conventional ERP analyses as well as multivariate support vector regression (SVR) analyses were conducted to predict participants' subsequent ratings. We found that only SVR allowed both ‘arousal’ and ‘time reference’ ratings to be predicted during the first 200 ms post-stimulus. This demonstrates an early, automatic semantic stimulus analysis, which might be related to the high relevance of ‘time reference’ to everyday decision-making and preference formation.

Decoding the Neuroanatomical Basis of Reading Ability: A Multivoxel Morphometric Study

As a relatively recent cultural invention in human evolution, reading is an important gateway to personal development and socioeconomic success. Despite the well documented individual differences in reading ability, its neuroanatomical correlates have not been well understood, largely due to the fact that reading is a complex skill that consists of multiple components. Using a large sample of 416 college students and 7 reading tasks, the present study successfully identified three uncorrelated components of reading ability: phonological decoding, form-sound association, and naming speed. We then tried to predict individuals' scores in these components from their gray matter volume (GMV) on a subset of participants (N = 253) with high-quality structural images, adopting a multivariate support vector regression analysis with tenfold cross-validation. Our results revealed distinct neural regions that supported different aspects of reading ability: whereas phonological decoding was associated with the GMV in the left superior parietal lobe extending to the supramarginal gyrus, form-sound association was predicted by the GMV in the hippocampus and cerebellum. Naming speed was associated with GMV in distributed brain regions in the occipital, temporal, parietal, and frontal cortices. Phonological decoding and form-sound association were uncorrelated with general cognitive abilities. However, naming speed was correlated with intelligence and processing speed, and some of the regions that were predictive of naming speed also predicted these general cognitive abilities. These results provide further insights on the cognitive and neural architecture of reading and the structural basis of individual differences in reading abilities.

Multivariate convex support vector regression with semidefinite programming

As one of important nonparametric regression method, support vector regression can achieve nonlinear capability by kernel trick. This paper discusses multivariate support vector regression when its regression function is restricted to be convex. This paper approximates this convex shape restriction with a series of linear matrix inequality constraints and transforms its training to a semidefinite programming problem, which is computationally tractable. Extensions to multivariate concave case, ℓ2-norm Regularization, ℓ1 and ℓ2-norm loss functions, are also studied in this paper. Experimental results on both toy data sets and a real data set clearly show that, by exploiting this prior shape knowledge, this method can achieve better performance than the classical support vector regression.