scholarly journals Extensive Audio-motor Experience Can Calibrate The Egocentric Space In Early Blindness

2021 ◽  
Author(s):  
Davide Esposito ◽  
Alice Bollini ◽  
Monica Gori
Keyword(s):  
Spatial Representation ◽  
Vision Loss ◽  
Single Case ◽  
Football Player ◽  
Support Vector ◽  
Visual Channel ◽  
Trunk Motion ◽  
Motor Experience ◽  
Auditory Scene ◽  
Overall Performance

Combining and integrating cues from different sensory channels is fundamental in developing a spatial representation of the environment. In the sighted population, the visual channel is essential in the spatial representation calibration; indeed, blind individuals show some impairments. One may compensate the vision loss to some degree by exploiting the associations between a movement and the consequent change in perceived auditory scene, known as audio-motor contingencies. The compensation extent is unclear, but evidence suggests that it depends on the amount of both visual and motor experience.To quantify the extent of audio-motor compensation in relation to motor and audio-motor experience, we tested the spatial representation skills of a long-experienced early blind 5-a-side football player. We focused on auditory localization performance and sensitivity to an audio-motor contingency alteration. The study compared the player to groups of early blind (audio-motor experience without specific training) and sighted blindfolded people. We also tested an additional early blind individual without extensive audio-motor experience but who lost vision at an older age than the player, to control the effect of early visual experience alone.Participants were tested on a set of steering tasks in auditory virtual reality (VR). In such tasks, participants would rotate a flying arrow towards an acoustic target. Rotations of the head or trunk controlled the arrow trajectory. Additionally, in some conditions, the relationship between movement and change of acoustic perceptual scene was altered to expose the participants’ sensitivity to the audio-motor contingency alteration.The early blind player performance was analyzed with classical univariate single-case statistics and a multivariate support vector machine classifier. Univariate analyses suggested that the early blind player’s trunk motion is early blind-like. However, the multivariate classifier interpreted his overall performance as that of a sighted individual. The multivariate classifier labelled the visually experienced early blind's overall performance as early blind-like. We concluded that extensive audio-motor experience could compensate for early vision loss for what concerns the sensitivity to audio-motor contingency alterations. These results support the idea that adapted sports for visually impaired people are useful to improve their spatial representation and, consequently, their quality of life.

scholarly journals Recurrent Intraocular Lens Dislocation in a Patient with Familial Ectopia Lentis

2021 ◽  
Vol 18 (9) ◽  
pp. 4545
Author(s):  
Tomasz K. Wilczyński ◽  
Alfred Niewiem ◽  
Rafał Leszczyński ◽  
Katarzyna Michalska-Małecka
Keyword(s):  
Intraocular Lens ◽  
Pars Plana Vitrectomy ◽  
Vision Loss ◽  
Silicone Oil ◽  
Single Case ◽  
Recurrent Dislocation ◽  
Ectopia Lentis ◽  
Pars Plana ◽  
The Right

A 36-year-old patient presented to the hospital with recurrent dislocation of the intraocular lens (IOL). The patient with the diagnosis of familial ectopia lentis was first operated on for crystalline lens subluxation in the left eye in 2007 and in the right eye in 2009. In both eyes, lens extraction with anterior vitrectomy and transscleral fixation of a rigid IOL was performed. In 2011, the IOL in the right eye luxated into the vitreous cavity due to ocular trauma. The patient underwent a pars plana vitrectomy with the IOL resuturation to the sclera. Seven years later, a spontaneous vision loss in the right eye was caused by a retinal detachment. The pars plana vitrectomy with silicone oil tamponade and a consequential oil removal three months later were performed in 2018. The follow-up examination revealed recurrent IOL dislocation in the same eye. Due to a history of previous suture-related complications a decision was made to remove the subluxated rigid polymethyl-methacrylate (PMMA) IOL and fixate to sclera a sutureless SOLEKO FIL SSF Carlevale lens. The purpose of this report is to present a single case of a 36-year-old patient who was presented to the hospital with recurrent dislocation of the intraocular lens. In a three-month follow-up period, a good anatomical and functional outcome was finally obtained with transscleral sutureless intraocular lens. This lens is an option worth considering especially in a young patient with a long life expectancy and physically active.

scholarly journals Impact of Dataset Size on Classification Performance: An Empirical Evaluation in the Medical Domain

2021 ◽  
Vol 11 (2) ◽  
pp. 796
Author(s):  
Alhanoof Althnian ◽  
Duaa AlSaeed ◽  
Heyam Al-Baity ◽  
Amani Samha ◽  
Alanoud Bin Dris ◽  
...  
Keyword(s):  
Empirical Evaluation ◽  
Classification Performance ◽  
Support Vector ◽  
Robust Model ◽  
Original Distribution ◽  
C4.5 Decision Tree ◽  
Dataset Size ◽  
Overall Performance ◽  
Medical Domain ◽  
The Impact

Dataset size is considered a major concern in the medical domain, where lack of data is a common occurrence. This study aims to investigate the impact of dataset size on the overall performance of supervised classification models. We examined the performance of six widely-used models in the medical field, including support vector machine (SVM), neural networks (NN), C4.5 decision tree (DT), random forest (RF), adaboost (AB), and naïve Bayes (NB) on eighteen small medical UCI datasets. We further implemented three dataset size reduction scenarios on two large datasets and analyze the performance of the models when trained on each resulting dataset with respect to accuracy, precision, recall, f-score, specificity, and area under the ROC curve (AUC). Our results indicated that the overall performance of classifiers depend on how much a dataset represents the original distribution rather than its size. Moreover, we found that the most robust model for limited medical data is AB and NB, followed by SVM, and then RF and NN, while the least robust model is DT. Furthermore, an interesting observation is that a robust machine learning model to limited dataset does not necessary imply that it provides the best performance compared to other models.

scholarly journals Morphological residual convolutional neural network (M-RCNN) for intelligent recognition of wear particles from artificial joints

Friction ◽  
2021 ◽  
Author(s):  
Xiaobin Hu ◽  
Jian Song ◽  
Zhenhua Liao ◽  
Yuhong Liu ◽  
Jian Gao ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Data Augmentation ◽  
Support Vector ◽  
Wear Particles ◽  
Artificial Joints ◽  
Performance Deterioration ◽  
Overall Performance ◽  
Correct Category ◽  
Intelligent Recognition

AbstractFinding the correct category of wear particles is important to understand the tribological behavior. However, manual identification is tedious and time-consuming. We here propose an automatic morphological residual convolutional neural network (M-RCNN), exploiting the residual knowledge and morphological priors between various particle types. We also employ data augmentation to prevent performance deterioration caused by the extremely imbalanced problem of class distribution. Experimental results indicate that our morphological priors are distinguishable and beneficial to largely boosting overall performance. M-RCNN demonstrates a much higher accuracy (0.940) than the deep residual network (0.845) and support vector machine (0.821). This work provides an effective solution for automatically identifying wear particles and can be a powerful tool to further analyze the failure mechanisms of artificial joints.

Support Vector Regression for Missing Data Estimation

2010 ◽  
pp. 117-141
Author(s):  
Tshilidzi Marwala
Keyword(s):  
Principal Component Analysis ◽  
Support Vector Regression ◽  
Principal Component ◽  
Component Analysis ◽  
Support Vector ◽  
Overall Performance ◽  
Accuracy Measures ◽  
Missing Variables ◽  
Missing Data Estimation ◽  
Data Estimation

This chapter develops and compares the merits of three different data imputation models by using accuracy measures. The three methods are auto-associative neural networks, a principal component analysis and support vector regression all combined with cultural genetic algorithms to impute missing variables. The use of a principal component analysis improves the overall performance of the auto-associative network while the use of support vector regression shows promising potential for future investigation. Imputation accuracies up to 97.4% for some of the variables are achieved.

Treatment of idiopathic intracranial hypertension via stereotactic placement of biventriculoperitoneal shunts

2018 ◽  
Vol 130 (1) ◽  
pp. 136-144 ◽  
Author(s):  
Michael Karsy ◽  
Hussam Abou-Al-Shaar ◽  
Christian A. Bowers ◽  
Richard H. Schmidt
Keyword(s):  
Intracranial Hypertension ◽  
Idiopathic Intracranial Hypertension ◽  
Vision Loss ◽  
Single Case ◽  
Distal Catheter ◽  
Shunt Placement ◽  
Presenting Symptoms ◽  
Small Series ◽  
Shunt Survival

OBJECTIVEIdiopathic intracranial hypertension (IIH), or pseudotumor cerebri, is a complex and difficult-to-manage condition that can lead to permanent vision loss and refractory headaches if untreated. Traditional treatment options, such as unilateral ventriculoperitoneal (VP) or lumboperitoneal (LP) shunt placement, have high complication and failure rates and often require multiple revisions. The use of bilateral proximal catheters has been hypothesized as a method to improve shunt survival. The use of stereotactic technology has improved the accuracy of catheter placement and may improve treatment of IIH, with fewer complications and greater shunt patency time.METHODSThe authors performed a retrospective chart review for all patients with IIH who underwent stereotactic placement of biventriculoperitoneal (BVP) shunt catheters from 2008 to 2016 at their institution. Bilateral proximal catheters were Y-connected to a Strata valve with a single distal catheter. We evaluated clinical, surgical, and ophthalmological variables and outcomes.RESULTSMost patients in this series of 34 patients (mean age 34.4 ± 8.2 years, mean body mass index 38.7 ± 8.3 kg/m2; 91.2% were women) undergoing 41 shunt procedures presented with headache (94.1%) and visual deficits (85.3%). The mean opening pressure was 39.6 ± 9.0 cm H2O. In addition, 50.0% had undergone previous unilateral shunt placement, and 20.6% had undergone prior optic nerve sheath fenestration. After BVP shunt placement, there were no cases of proximal catheter obstruction and only a single case of valve obstruction at 41.9 months, with a mean follow-up of 24.8 ± 20.0 months. Most patients showed improvement in their headache (82.4%), subjective vision (70.6%), and papilledema (61.5% preoperatively vs 20.0% postoperatively, p = 0.02) at follow-up. Additional primary complications included 4 patients with migration of their distal catheters out of the peritoneum (twice in 1 patient), and an infection of the distal catheter after catheter dislodgment. The proximal obstructive shunt complication rate in this series (2.9%) was lower than that with LP (53.5%) or unilateral VP (37.8%) shunts seen in the literature.CONCLUSIONSThis small series suggests that stereotactic placement of BVP shunt catheters appears to improve shunt survival rates and presenting symptoms in patients with IIH. Compared with unilateral VP or LP shunts, the use of BVP shunts may be a more effective and more functionally sustained method for the treatment of IIH.

CURVELET FUSION ENHACEMENT BASED EVALUATION OF DIABETIC RETINOPATHY BY THE IDENTIFICATION OF EXUDATES IN OPTIC COLOR FUNDUS IMAGES

2016 ◽  
Vol 28 (06) ◽  
pp. 1650046
Author(s):  
V. Ratna Bhargavi ◽  
Ranjan K. Senapati
Keyword(s):  
Diabetic Retinopathy ◽  
Vision Loss ◽  
Detection System ◽  
Clinical Signs ◽  
Posterior Part ◽  
Curvelet Transform ◽  
Optic Disk ◽  
Support Vector ◽  
Fundus Images ◽  
Statistical Measures

Rapid growth of Diabetes mellitus in people causes damage to posterior part of eye vessel structures. Diabetic retinopathy (DR) is an important hurdle in diabetic people and it causes lesion formation in retina due to retinal vessel structures damage. Bright lesions (BLs) or exudates are initial clinical signs of DR. Early BLs detection can help avoiding vision loss. The severity can be recognized based on number of BLs formed in the color fundus image. Manually diagnosing a large amount of images is time consuming. So a computerized DR grading and BLs detection system is proposed. In this paper for BLs detection, curvelet fusion enhancement is done initially because bright objects maps to largest coefficients in an image by utilizing the curvelet transform, so that BLs can be recognized in the retina easily. Then optic disk (OD) appearance is similar to BLs and vessel structures are barriers for lesion exact detection and moreover OD falsely classified as BLs and that increases false positives in classification. So these structures are segmented and eliminated by thresholding techniques. Various features were obtained from detected BLs. Publicly available databases are used for DR severity testing. 260 fundus images were used for the performance evaluation of proposed work. The support vector machine classifier (SVM) used to separate fundus images in various levels of DR based on feature set extracted. The proposed system that obtained the statistical measures were sensitivity 100%, specificity 95.4% and accuracy 97.74%. Compared to existing state-of-art techniques, the proposed work obtained better results in terms of sensitivity, specificity and accuracy.

scholarly journals A Vision based Indian Traffic Sign Classification

2020 ◽  
Vol 8 (6) ◽  
pp. 3132-3141
Keyword(s):  
Support Vector ◽  
Svm Classifier ◽  
Traffic Sign ◽  
Illumination Variation ◽  
Svm Algorithm ◽  
Speed Up ◽  
Surf Features ◽  
Overall Performance ◽  
Whisker Plot ◽  
Traffic Sign Classification

In this paper, an algorithm is proposed to classify the Indian traffic sign as mandatory cautionary and informatory class. In order to complete the task, system extracted the speed up robust features (SURF) from the Indian traffic sign data, and exploited these features to train support vector machine (SVM) algorithm. Combination of SURF features and SVM classifier makes system robust for scale variation, rotation, translation and illumination variation as well as generalization is achieved. Dimension of features have been reduced by choosing a sub set of features. Whisker and box plot visualization utilized to understand the features data. Whisker plot visualization concluded about the range, skewness, median and outliers of feature data therefore, it makes the system capable to keep good features and back out from irrelevant features. Feature refinement reduces the computational complexity. The results evaluated narrate that the overall performance of proposed algorithm is efficient.

scholarly journals Automatic Detection and Localization of Macular Edema

2020 ◽  
Vol 5 (9) ◽  
pp. 552-558
Author(s):  
S. Sumithra ◽  
K. R. Remya ◽  
Dr. M. N. Giri Prasad
Keyword(s):  
Macular Edema ◽  
Vision Loss ◽  
Automatic Detection ◽  
Detection Algorithm ◽  
Support Vector ◽  
Fisher Linear Discriminant ◽  
Linear Discriminant ◽  
The People ◽  
Simple Linear Iterative Clustering ◽  
Detection And Localization

Diabetic retinopathy is an eye disease and causes vision loss to the people who are suffering longer from the diabetes. Exudates, bright and red lesions are identified in the diabetic retinal eye. Automatic detection and localization of macular edema is a challenging issue since exudates have non uniform illumination and are low contrasted. Proposed algorithm to detect macular edema encompasses Simple Linear Iterative Clustering, Fisher linear discriminant and Support vector machine classifer. Optic Disc extraction prior to exudates extraction is also introduced. Performance of the proposed detection algorithm is tested on easily available databases: Diaretdb1, Messidor and E_optha Ex. Proposed method shows an accuracy of 97.81%, specificity 98.65 and Sensitivity 82.71%.

scholarly journals Ensemble probability distribution for novelty detection

2018 ◽  
Vol 189 ◽  
pp. 03008
Author(s):  
Xiaoshuang Qiao ◽  
Hui Wang ◽  
Gongde Guo ◽  
Yuanyuan Liu
Keyword(s):  
Probability Distribution ◽  
Real World ◽  
Mixed Models ◽  
Novelty Detection ◽  
The Other ◽  
Support Vector ◽  
Ensemble Approach ◽  
Overall Performance ◽  
Real World Datasets ◽  
Domain Description

This paper explores a new ensemble approach called Ensemble Probability Distribution Novelty Detection (EPDND) for novelty detection. The proposed ensemble approach provides a metric to characterize different classes. Experimental results on 4 real-world datasets show that EPDND exhibits competitive overall performance to the other two common novelty detection approaches - Support Vector Domain Description and Gaussian Mixed Models in terms of accuracy, recall and F1 scores in many cases.

Sign in / Sign up

Export Citation Format

Share Document