Feature optimization and creation of a real time pattern matching system

BackgroundHuman cognitive processing speed is known to decline with age. Human cognitive processing speed refers to the time that an individual takes from receiving a stimulus to reacting to it. Serious games, which are video games used for training and educational purposes, have the potential to improve processing speed. Numerous systematic reviews have summarized the evidence regarding the effectiveness of serious games in improving processing speed, but they are undermined by some limitations.ObjectiveThis study aimed to examine the effectiveness of serious games on the cognitive processing speed of an older adult population living with cognitive impairment.MethodsA systematic review of randomized controlled trials (RCTs) was conducted. Two search sources were used in this review: 8 electronic databases and backward and forward reference list checking. A total of 2 reviewers independently checked the eligibility of the studies, extracted data from the included studies, and appraised the risk of bias and quality of the evidence. Evidence from the included studies was synthesized using a narrative and statistical approach (ie, meta-analysis), as appropriate.ResultsOf the 548 publications identified, 16 (2.9%) RCTs eventually met all eligibility criteria. Very-low-quality evidence from 50% (8/16) and 38% (6/16) of the RCTs showed no statistically significant effect of serious games on processing speed compared with no or passive intervention groups (P=.77) and conventional exercises (P=.58), respectively. A subgroup analysis showed that both types of serious games (cognitive training games: P=.26; exergames: P=.88) were as effective as conventional exercises in improving processing speed.ConclusionsThere is no superiority of serious games over no or passive interventions and conventional exercises in improving processing speed among older adults with cognitive impairment. However, our findings remain inconclusive because of the low quality of the evidence, the small sample size in most of the included studies, and the paucity of studies included in the meta-analyses. Therefore, until more robust evidence is published, serious games should be offered or used as an adjunct to existing interventions. Further trials should be undertaken to investigate the effect of serious games that specifically target processing speed rather than cognitive abilities in general.Trial RegistrationPROSPERO CRD42022301667; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=301667

Automated accurate fire detection system using ensemble pretrained residual network

Magnetic Resonance images are used to identify tears in the meniscus, a debilitating condition of the knee. In this paper, a two-staged computerized system for diagnosing meniscus tears is proposed. In the first stage, we apply an Active Contour with Level Sets model to calculate the location and shape of the meniscus area. In the second stage, 180 features, consisting of textural information in the spatial and spectral domains, were extracted from each suspected meniscus tear. Sequential floating forward selection (SFFS) was applied to select the relevant features. The feature vectors were then input to a support vector machine (SVM) classifier to detect meniscus tears. The Az value of the receiver operating characteristic (ROC) curve were used to evaluate the classification performance. Experimental results show that the dimension of the feature vector was reduced from 180 to 64 after the SFFS. Meanwhile, the SVM classifier combined with the SFFS feature selection (Az = 0.9123) outperformed the SVM classifier without feature selection (Az = 0.7273).

Vehicle detection and tracking plays a major role in military and civilian applications. The accurate detection of multiple vehicles in a complicated traffic environment is too difficult. This process is made more difficult, if there are occlusions between vehicles. The optimal feature selection of a vehicle is also a challenging task. These issues are focused in the existing work namely convolution neural network (CNN) based vehicle detection. However in this work, feature selection is not concentrated and with the lesser feature information classification accuracy is reduced considerably. This is focused and resolved in the proposed research by introducing the method namely Enhanced Convolution neural network with Support Vector Machine (ECNN-SVM) based vehicle detection. In this work initially feature extraction is done. Haar like features are used for this purpose. This has compact representation, capture information from multiple scales, encoded edge and structural information and can be efficient computation. Haar like feature pool is large scale in nature. Enhanced bat optimization is used to select features from this pool. This selection is done by combining sample’s class label and feature value. Confidence level between two thresholds of tracking rectangles is used for classification. Support vector machine (SVM) classifier is combined with local binary pattern to perform this classification. The interference areas between moving objects and vehicles are removed by Enhanced Convolutional Neural Network (ECNN) classifier. The efficiency of the proposed method is computed by using experimental and theoretical analysis.

Biomedical data are widely accepted in developing prediction models for identifying a specific tumour, drug discovery and human cancers detection. However, previous studies usually focused on different classifiers, and overlook the class imbalance problem in real-world biomedical datasets. This paper mainly focuses on reviewing and evaluating some popular and recently developed resampling and feature selection (FS) methods for class imbalance learning with data distribution being considered. Experimental results show that: 1) resampling and FS techniques exhibit better performance using support vector machine (SVM) classifier; 2) techniques such as random undersampling and FS perform better than other data pre-processing methods with T location-scale distribution when using SVM and K-nearest neighbours (KNN) classifiers. Random oversampling outperforms other methods on negative binomial distribution using Random Forest with lower level of imbalance ratio; 3) FS outperforms other data pre-processing methods in most cases, thus, FS with SVM classifier is the best choice for imbalanced biomedical data learning.

Optimal feature selection for classification of the power quality events using wavelet transform and least squares support vector machines

Pluripotent stem cells can potentially be used in clinical applications as a model for studying disease progress. This tracking of disease-causing events in cells requires constant assessment of the quality of stem cells. Existing approaches are inadequate for robust and automated differentiation of stem cell colonies. In this study, we developed a new model of vector–based convolutional neural network (V-CNN) with respect to extracted features of the induced pluripotent stem cell (iPSC) colony for distinguishing colony characteristics. A transfer function from the feature vectors to the virtual image was generated at the front of the CNN in order for classification of feature vectors of healthy and unhealthy colonies. The robustness of the proposed V-CNN model in distinguishing colonies was compared with that of the competitive support vector machine (SVM) classifier based on morphological, textural, and combined features. Additionally, five-fold cross-validation was used to investigate the performance of the V-CNN model. The precision, recall, and F-measure values of the V-CNN model were comparatively higher than those of the SVM classifier, with a range of 87–93%, indicating fewer false positives and false negative rates. Furthermore, for determining the quality of colonies, the V-CNN model showed higher accuracy values based on morphological (95.5%), textural (91.0%), and combined (93.2%) features than those estimated with the SVM classifier (86.7, 83.3, and 83.4%, respectively). Similarly, the accuracy of the feature sets using five-fold cross-validation was above 90% for the V-CNN model, whereas that yielded by the SVM model was in the range of 75–77%. We thus concluded that the proposed V-CNN model outperforms the conventional SVM classifier, which strongly suggests that it as a reliable framework for robust colony classification of iPSCs. It can also serve as a cost-effective quality recognition tool during culture and other experimental procedures.

This study investigated the effect of a new approach, the support vector machine, as a classifier tool to identify the weeds in corn fields at early growth stage. Image segmentation was done by transforming original color images to gray level images according to the statistical values of red, green, blue components. The Gray Level Co-occurrence Matrix (GLCM) and statistical properties of the histogram from the gray level images were further used to obtain the texture features of the weeds and corn seedlings. These texture features were used in the classification procedure. Principle component analysis was used to select the texture features according to their better contributions to reduce space dimensions. A Support Vector Machine (SVM) classifier was employed to recognize the weeds and the corn seedlings. The results indicated that the SVM classifiers with different feature selections could identify successfully weed-corn with a higher accuracy ranged from 92.31 to 100%. A comparison study of the recognition capabilities of SVM and back-propagation (BP) neural-network classifier using the same data set was conducted. It was found that the SVM classifier provided the best recognition performance with an accuracy of 100%, which exceeded the accuracy of 80% given by the BP classifier. Key words: Corn seedling, weeds, texture, support vector machine, recognize.

Strength and balance retraining exercises reduce the rate of subsequent falls in community-dwelling older adults who have previously fallen. Exercise can also improve cognitive function, including processing speed. Given processing speed predicts subsequent falls, we aimed to determine whether improved processing speed mediated the effects of the Otago Exercise Program on the rate of subsequent: (i) total falls, (ii) non-injurious falls, (iii) moderate injurious falls, and (iv) serious injurious falls. A secondary complete case analysis of a 12-month, single-blind, randomized clinical trial among 256 of 344 adults aged at least 70 years who fell in the previous 12 months. Participants were randomized 1:1 to receive usual care plus the Otago Exercise Program (n = 123) or usual care (n = 133), consisting of fall prevention care provided by a geriatrician. The primary outcome was self-reported number of falls over 12 months (ie, rate of falls). Processing speed was assessed at baseline and at 12 months by the Digit Symbol Substitution Test (DSST). Causal mediation analyses were conducted using quasi-Bayesian estimates and 95% confidence intervals. Exercise significantly reduced the rate of subsequent moderate injurious falls (IRR = 0.49; 95% CI: 0.31, 0.77; p = .002) and improved processing speed (estimated mean difference: 1.16 points; 95% CI: 0.11, 2.21). Improved DSST mediated the effect of exercise on the rate of subsequent moderate injurious falls (estimate: -0.06; 95% CI: -0.15, -0.001; p = .036). Improved processing speed may be a mechanism by which exercise reduces subsequent moderate injurious falls in older adults who fell previously. ClinicalTrials.gov Protocol Registration System:NCT01029171: https://clinicaltrials.gov/ct2/show/NCT01029171NCT00323596: https://clinicaltrials.gov/ct2/show/NCT00323596.

To evaluate the effects of methylphenidate on a variety of aspects of attention, ranging from laboratory-based impairment measures to caregiver ratings and work productivity, in individuals after traumatic brain injury. A total of 34 adults with moderate to severe traumatic brain injury and attention complaints in the postacute phase of recovery were enrolled in a 6-wk, double-blind, placebo-controlled, repeated crossover study of methylphenidate, administered in a dose of 0.3 mg/kg/dose, twice a day. A wide range of attentional measures was gathered weekly, including computerized and paper-and-pencil tests of attention, videotaped records of individual work in a distracting environment, real-time observational scoring of attentiveness in a classroom environment, and caregiver and clinician rating scales of attentiveness. Participants also attempted to guess their drug condition each week. Data from the first ten participants were used for pilot purposes, to develop attentional factors for composite scoring, and to identify attentional dimensions suggestive of a treatment effect for independent replication. The remaining 24 participants' results were used to confirm potential treatment effects seen in the pilot sample, using Wilcoxon's signed-ranks test on composite factor scores and individual variables. A total of 54 dependent variables were reduced to 13 composite factors and 13 remaining individual variables. Of the 13 attentional factors, five showed suggestive treatment effects in the pilot sample. Of these, three showed statistically significant treatment effects in the replication sample: speed of information processing (effect sizes, -0.06 to 0.48; P < 0.001), attentiveness during individual work tasks (effect sizes, 0.15-0.62; P = 0.01), and caregiver ratings of attention (effect sizes, 0.44-0.50; P = 0.01). Of the individual variables, four showed suggestive treatment effects in the pilot sample, but only one showed significant treatment effects in the replication sample: reaction time before errors in the Sustained Attention to Response Task (effect size, 0.20; P = 0.03). No treatment-related improvement was seen in divided attention, sustained attention, or susceptibility to distraction. None of the variables showed suggestive or definite negative treatment effects. Effect sizes for those performance measures positively affected by methylphenidate were in the small to medium range and included both impairment and activity level measures. Improvements in processing speed did not seem to come at the expense of accuracy. Methylphenidate, at 0.3 mg/kg/dose, given twice a day to individuals with attentional complaints after traumatic brain injury, seems to have clinically significant positive effects on speed of processing, caregiver ratings of attention, and some aspects of on-task behavior in naturalistic tasks. Further research is needed to identify the optimal dose and to extend these findings to less carefully selected individuals.

This 24-week randomized controlled trial study evaluated the effects of two interactive cognitive–motor programs on body composition, lower-body strength, and processing speed in community dwellings at risk of falling. Forty-eight participants (75.0 ± 5.4 years) were allocated into EG1 (psychomotor intervention program), EG2 (combined program (psychomotor intervention + whole-body vibration)), and a control group. EG programs induced significant improvements in bone mass, lower-body strength, and processing speed (p < 0.05), with similar treatment effects on lower-body strength and processing speed and higher bone mineral content and density within EG2. The fall rate decreased in EG1 (44.2%) and EG2 (63%) (p < 0.05). After the 12-week no-intervention follow-up, improvements in lower-body strength were reversed in both EGs, but those in processing speed were maintained, mainly in EG2 (p < 0.05). In conclusion, both programs were accepted and well tolerated. The combined program led to additional benefits in bone mass. Both programs positively impacted physical and cognitive risk factors for falls and injuries. They induced similar improvements in lower-body strength and processing speed, decreasing the fall rate. These findings suggest that both programs are successful for fall and injury prevention in the studied population.

In many pattern recognition applications feature selection and instance selection can be used as two data preprocessing methods that aim at reducing the computational cost of the learning process. Moreover, in some cases, feature subset selection can improve the classification performance. Feature selection and instance selection can be interesting since the choice of features and instances greatly influence the performance of the learnt models as well as their training costs. In the past, unifying both problems was carried out by solving a global optimization problem using meta-heuristics. This paradigm not only does not exploit the manifold structure of data but can be computationally expensive. To the best of our knowledge, the joint use of sparse modeling representative and feature subset relevance have not been exploited by the joint feature and selection methods. In this paper, we target the joint feature and instance selection by adopting feature subset relevance and sparse modeling representative selection. More precisely, we propose three schemes for the joint feature and instance selection. The first is a wrapper technique while the two remaining ones are filter approaches. In the filter approaches, the search process adopts a genetic algorithm in which the evaluation is mainly given by a score that quantify the goodness of the features and instances. An efficient instance selection technique is used and integrated in the search process in order to adapt the instances to the candidate feature subset. We evaluate the performance of the proposed schemes using image classification where classifiers are the nearest neighbor classifier and support vector machine classifier. The study is conducted on five public image datasets. These experiments show the superiority of the proposed schemes over various baselines. The results confirm that the filter approaches leads to promising improvement on classification accuracy when both feature selection and instance selection are adopted.

Ketamine has proven to have rapid, robust antidepressant effects on treatment-resistant depression. However, whether repeated ketamine infusions would cause short-and long-term neurocognitive impairments was not clear. Our aims were to investigate the neurocognitive effects of six ketamine infusions and to examine the association between these infusions and the antidepressant response in patients with unipolar and bipolar depression. Six intravenous infusions of ketamine (0.5 mg/kg) over a 12-day period were administered to 84 patients with unipolar and bipolar depression. Severity of depressive symptoms and four domains of neurocognition, including speed of processing, working memory, visual learning and verbal learning, were assessed at baseline, one day following the last infusion and again two weeks post-infusion. Significant improvements were found on speed of processing ( F=9.344, p<0.001) and verbal learning ( F=5.647, p=0.004) in a linear mixed model. The Sobel test showed significant indirect effects between time and improvement in speed of processing (Sobel test=3.573, p<0.001) as well as improvement in verbal learning (Sobel test=6.649, p<0.001), which were both significantly mediated by change in depressive symptoms. Logistic regression analysis showed ketamine responders had better visual learning at baseline than non-responders (B=0.118, p<0.001). Our findings suggest that neurocognitive function would not deteriorate after six ketamine infusions, while verbal learning and speed of processing improved over 13 days and 26 days of observation, respectively. However, this change was mainly accounted for by improvements in severity of depressive symptoms over time. Greater baseline visual learning predicted an antidepressant response over six ketamine infusions.

BackgroundSTRIVE was a prospective, 4-year, multicenter, observational, open-label, single-arm study of natalizumab treatment in anti-JC virus antibody-negative patients with early relapsing-remitting multiple sclerosis (RRMS).ObjectiveStudy objectives examined the effects of natalizumab on cognitive processing speed, confirmed disability improvement (CDI), and patient-reported outcomes (PROs).MethodsClinical and PRO secondary endpoints were assessed annually over 4 years in STRIVE. The Symbol Digit Modalities Test (SDMT) was used as a measure of cognitive processing speed. PROs were assessed using the Multiple Sclerosis Impact Score (MSIS-29) and the Work Productivity and Activity Impairment Questionnaire (WPAI).ResultsAt all four annual assessments, the proportion of patients in the intent-to-treat (ITT) population (N = 222) who exhibited clinically meaningful improvement in their SDMT score from baseline (i.e., change ≥ 4 points) ranged from 41.9 to 54.0%. The cumulative probability of CDI at 4 years in patients in the ITT population with a baseline Expanded Disability Status Scale score ≥ 2 (N = 133) was 43.9%. Statistically significant reductions in the mean change from screening in the MSIS-29 physical and psychological scores, indicating improved quality of life, were observed over all 4 years (P ≤ 0.0012 for all). A statistically significant decrease from screening in the impact of MS on regular activities, signifying an improvement in this WPAI measure, was also observed over all 4 years of the study.ConclusionThese results further extend our knowledge of the effectiveness, specifically regarding improvements in cognitive processing speed, disability and PROs, of long-term natalizumab treatment in early RRMS patients.Clinicaltrials.govNCT01485003 (5 December 2011)

Successful classification depends on the selection of the distinctive features and the effective channel subset used in the classification. In this study, novel and practical methods are proposed for determining the distinctive features and detecting effective channel subsets in the multi channel classification systems such as EEG. Two different feature extraction methods are compared in the study. The first one is based on classical Wavelet transform and the second is our proposed approach which used the slope of signal segments. Feature vectors are generated from some signal properties such as the mean, standard deviation, numerical integral of the Wavelet coefficients for classical Wavelet transform based feature extraction method. For our proposed method, only the slopes of signal segments are used for the feature vectors. In the proposed Signal Path Slope (SPS) feature extraction method, differently from the classical Wavelet based method, a Savitzky Golay (S-G) filter with an optimal frame length is applied to the signal before segmentation to make the path of the signal more prominent in time domain. In this way, the distinctive classification features are extracted by using S-G filter. For channel selection, an iterative channel selection method based on the classification results which divide the dataset labelled dataset into two groups as % 90 pre-training and %10 pre-test data is proposed. The dataset provided as dataset-3 in BCI competition IV is used in this study. The feature vectors extracted by using the proposed methods are classified for each method with the Support Vector Machine classifier. The results are given comparatively and it is observed that our proposed method has less computational complexity and more successful classification than Wavelet based classical feature extraction methods. The highest classification accuracies of % 67.74 and % 49.27 for subject-1 and subject-2 respectively are obtained with a low dimensional feature vector by proposed SPS feature extraction method. The classification accuracies achieved in the study are increased by % 8.24 for subject-1 and % 14.97 for subject-2 when compared average of the competition results. The significant increase in the success for both subjects shows the consistency of the proposed methods. By this study, it is observed that there is a subject-specific signal pattern related to motor imagery tasks in the brain. This pattern distinctive features is successfully determined by using the proposed methods.