scholarly journals An Application of Deep Learning to Tactile Data for Object Recognition under Visual Guidance

Sensors ◽  
2019 ◽  
Vol 19 (7) ◽  
pp. 1534 ◽  
Author(s):  
Ghazal Rouhafzay ◽  
Ana-Maria Cretu
Keyword(s):  
Object Recognition ◽  
Visual Attention ◽  
Visual Information ◽  
Support Vector ◽  
Sequential Data ◽  
K Nearest Neighbors ◽  
Object A ◽  
Haptic Exploration ◽  
Virtual Force ◽  
Neuroscience Research

Drawing inspiration from haptic exploration of objects by humans, the current work proposes a novel framework for robotic tactile object recognition, where visual information in the form of a set of visually interesting points is employed to guide the process of tactile data acquisition. Neuroscience research confirms the integration of cutaneous data as a response to surface changes sensed by humans with data from joints, muscles, and bones (kinesthetic cues) for object recognition. On the other hand, psychological studies demonstrate that humans tend to follow object contours to perceive their global shape, which leads to object recognition. In compliance with these findings, a series of contours are determined around a set of 24 virtual objects from which bimodal tactile data (kinesthetic and cutaneous) are obtained sequentially and by adaptively changing the size of the sensor surface according to the object geometry for each object. A virtual Force Sensing Resistor array (FSR) is employed to capture cutaneous cues. Two different methods for sequential data classification are then implemented using Convolutional Neural Networks (CNN) and conventional classifiers, including support vector machines and k-nearest neighbors. In the case of conventional classifiers, we exploit contourlet transformation to extract features from tactile images. In the case of CNN, two networks are trained for cutaneous and kinesthetic data and a novel hybrid decision-making strategy is proposed for object recognition. The proposed framework is tested both for contours determined blindly (randomly determined contours of objects) and contours determined using a model of visual attention. Trained classifiers are tested on 4560 new sequential tactile data and the CNN trained over tactile data from object contours selected by the model of visual attention yields an accuracy of 98.97% which is the highest accuracy among other implemented approaches.

Coordination of what and where in Visual Attention

Perception ◽  
1993 ◽  
Vol 22 (11) ◽  
pp. 1261-1270 ◽  
Author(s):  
John Duncan
Keyword(s):  
Object Recognition ◽  
Visual Attention ◽  
Divided Attention ◽  
Visual Information ◽  
Functional Relationship ◽  
Human Subjects ◽  
Visual Display ◽  
Spatial Relations ◽  
Cortical Areas ◽  
Cortical System

Performance often suffers when two visual discriminations must be made concurrently (‘divided attention’). In the modular primate visual system, different cortical areas analyse different kinds of visual information. Especially important is a distinction between an occipitoparietal ‘where?’ system, analysing spatial relations, and an occipitotemporal ‘what?’ system responsible for object recognition. Though such visual subsystems are anatomically parallel, their functional relationship when ‘what?’ and ‘where?’ discriminations are made concurrently is unknown. In the present experiments, human subjects made concurrent discriminations concerning a brief visual display. Discriminations were either similar (two ‘what?’ or two ‘where?’ discriminations) or dissimilar (one of each), and concerned the same or different objects. When discriminations concerned different objects, there was strong interference between them. This was equally severe whether discriminations were similar—and therefore dependent on the same cortical system—or dissimilar. When concurrent ‘what?’ and ‘where?’ discriminations concerned the same object, however, all interference disappeared. Such results suggest that ‘what?’ and ‘where?’ systems are coordinated in visual attention: their separate outputs can be used simultaneously without cost, but only when they concern one object.

scholarly journals A Visuo-Haptic Framework for Object Recognition Inspired by Human Tactile Perception

Proceedings ◽  
2019 ◽  
Vol 4 (1) ◽  
pp. 47 ◽  
Author(s):  
Ghazal Rouhafzay ◽  
Ana-Maria Cretu
Keyword(s):  
Support Vector ◽  
Self Organizing Map ◽  
Sensor Surface ◽  
Exploration Process ◽  
3D Objects ◽  
Haptic Exploration ◽  
Eye Fixations ◽  
Virtual Force ◽  
Tactile Image ◽  
Exploratory Procedure

This paper addresses the issue of robotic haptic exploration of 3D objects using an enhanced model of visual attention, where the latter is applied to obtain a sequence of eye fixations on the surface of objects guiding the haptic exploratory procedure. According to psychological studies, somatosensory data resulting as a response to surface changes sensed by human skin are used in combination with kinesthetic cues from muscles and tendons to recognize objects. Drawing inspiration from these findings, a series of five sequential tactile images are obtained by adaptively changing the size of the sensor surface according to the object geometry for each object, from various viewpoints, during an exploration process. We take advantage of the contourlet transform to extract several features from each tactile image. In addition to these somatosensory features, other kinesthetic inputs including the probing locations and the angle of the sensor surface with respect to the object in consecutive contacts are added as features. The dimensionality of the large feature vector is then reduced using a self-organizing map. Overall, 12 features from each sequence are concatenated and used for classification. The proposed framework is applied to a set of four virtual objects and a virtual force sensing resistor array (FSR) is used to capture tactile (haptic) imprints. Trained classifiers are tested to recognize data from new objects belonging to the same categories. Support vector machines yield the highest accuracy of 93.45%.

scholarly journals Use of Machine Learning to Investigate the Quantitative Checklist for Autism in Toddlers (Q-CHAT) towards Early Autism Screening

Diagnostics ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 574
Author(s):  
Gennaro Tartarisco ◽  
Giovanni Cicceri ◽  
Davide Di Pietro ◽  
Elisa Leonardi ◽  
Stefania Aiello ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Performance ◽  
Behavioral Science ◽  
Autistic Traits ◽  
Classification Performance ◽  
Recursive Feature Elimination ◽  
Diagnostic Tools ◽  
Support Vector ◽  
K Nearest Neighbors ◽  
Autism Screening

In the past two decades, several screening instruments were developed to detect toddlers who may be autistic both in clinical and unselected samples. Among others, the Quantitative CHecklist for Autism in Toddlers (Q-CHAT) is a quantitative and normally distributed measure of autistic traits that demonstrates good psychometric properties in different settings and cultures. Recently, machine learning (ML) has been applied to behavioral science to improve the classification performance of autism screening and diagnostic tools, but mainly in children, adolescents, and adults. In this study, we used ML to investigate the accuracy and reliability of the Q-CHAT in discriminating young autistic children from those without. Five different ML algorithms (random forest (RF), naïve Bayes (NB), support vector machine (SVM), logistic regression (LR), and K-nearest neighbors (KNN)) were applied to investigate the complete set of Q-CHAT items. Our results showed that ML achieved an overall accuracy of 90%, and the SVM was the most effective, being able to classify autism with 95% accuracy. Furthermore, using the SVM–recursive feature elimination (RFE) approach, we selected a subset of 14 items ensuring 91% accuracy, while 83% accuracy was obtained from the 3 best discriminating items in common to ours and the previously reported Q-CHAT-10. This evidence confirms the high performance and cross-cultural validity of the Q-CHAT, and supports the application of ML to create shorter and faster versions of the instrument, maintaining high classification accuracy, to be used as a quick, easy, and high-performance tool in primary-care settings.

scholarly journals Student Performance Prediction with Optimum Multilabel Ensemble Model

2021 ◽  
Vol 30 (1) ◽  
pp. 511-523
Author(s):  
Ephrem Admasu Yekun ◽  
Abrahaley Teklay Haile
Keyword(s):  
High School Students ◽  
Prediction Model ◽  
Student Performance ◽  
Performance Prediction ◽  
Transformation Method ◽  
Classification Task ◽  
Support Vector ◽  
School Students ◽  
K Nearest Neighbors ◽  
Classifier Chains

Abstract One of the important measures of quality of education is the performance of students in academic settings. Nowadays, abundant data is stored in educational institutions about students which can help to discover insight on how students are learning and to improve their performance ahead of time using data mining techniques. In this paper, we developed a student performance prediction model that predicts the performance of high school students for the next semester for five courses. We modeled our prediction system as a multi-label classification task and used support vector machine (SVM), Random Forest (RF), K-nearest Neighbors (KNN), and Multi-layer perceptron (MLP) as base-classifiers to train our model. We further improved the performance of the prediction model using a state-of-the-art partitioning scheme to divide the label space into smaller spaces and used Label Powerset (LP) transformation method to transform each labelset into a multi-class classification task. The proposed model achieved better performance in terms of different evaluation metrics when compared to other multi-label learning tasks such as binary relevance and classifier chains.

scholarly journals Variety Identification of Orchids Using Fourier Transform Infrared Spectroscopy Combined with Stacked Sparse Auto-Encoder

Molecules ◽  
2019 ◽  
Vol 24 (13) ◽  
pp. 2506 ◽  
Author(s):  
Yunfeng Chen ◽  
Yue Chen ◽  
Xuping Feng ◽  
Xufeng Yang ◽  
Jinnuo Zhang ◽  
...  
Keyword(s):  
Fourier Transform ◽  
Principal Component ◽  
Fourier Transform Infrared ◽  
Spectroscopic Technique ◽  
Variety Identification ◽  
Support Vector ◽  
K Nearest Neighbors ◽  
Discriminant Models ◽  
The Fourier Transform ◽  
Better Than

The feasibility of using the fourier transform infrared (FTIR) spectroscopic technique with a stacked sparse auto-encoder (SSAE) to identify orchid varieties was studied. Spectral data of 13 orchids varieties covering the spectral range of 4000–550 cm−1 were acquired to establish discriminant models and to select optimal spectral variables. K nearest neighbors (KNN), support vector machine (SVM), and SSAE models were built using full spectra. The SSAE model performed better than the KNN and SVM models and obtained a classification accuracy 99.4% in the calibration set and 97.9% in the prediction set. Then, three algorithms, principal component analysis loading (PCA-loading), competitive adaptive reweighted sampling (CARS), and stacked sparse auto-encoder guided backward (SSAE-GB), were used to select 39, 300, and 38 optimal wavenumbers, respectively. The KNN and SVM models were built based on optimal wavenumbers. Most of the optimal wavenumbers-based models performed slightly better than the all wavenumbers-based models. The performance of the SSAE-GB was better than the other two from the perspective of the accuracy of the discriminant models and the number of optimal wavenumbers. The results of this study showed that the FTIR spectroscopic technique combined with the SSAE algorithm could be adopted in the identification of the orchid varieties.

Persian Handwritten Number Recognition Using Adapted Framing Feature and Support Vector Machines

2016 ◽  
Vol 15 (01) ◽  
pp. 1650004 ◽  
Author(s):  
Hedieh Sajedi ◽  
Mehran Bahador
Keyword(s):  
Support Vector Machines ◽  
Recognition Rate ◽  
Nearest Neighbors ◽  
Polynomial Kernel ◽  
Support Vector ◽  
K Nearest Neighbors ◽  
New Approach ◽  
Number Recognition ◽  
Vector Machines

In this paper, a new approach for segmentation and recognition of Persian handwritten numbers is presented. This method utilizes the framing feature technique in combination with outer profile feature that we named this the adapted framing feature. In our proposed approach, segmentation of the numbers into digits has been carried out automatically. In the classification stage of the proposed method, Support Vector Machines (SVM) and k-Nearest Neighbors (k-NN) are used. Experimentations are conducted on the IFHCDB database consisting 17,740 numeral images and HODA database consisting 102,352 numeral images. In isolated digit level on IFHCDB, the recognition rate of 99.27%, is achieved by using SVM with polynomial kernel. Furthermore, in isolated digit level on HODA, the recognition rate of 99.07% is achieved by using SVM with polynomial kernel. The experiments illustrate that applying our proposed method resulted higher accuracy compared to previous researches.

Fast-HPLC Fingerprinting to Discriminate Olive Oil from Other Edible Vegetable Oils by Multivariate Classification Methods

2017 ◽  
Vol 100 (2) ◽  
pp. 345-350 ◽  
Author(s):  
Ana M Jiménez-Carvelo ◽  
Antonio González-Casado ◽  
Estefanía Pérez-Castaño ◽  
Luis Cuadros-Rodríguez
Keyword(s):  
Olive Oil ◽  
Vegetable Oils ◽  
Edible Oils ◽  
Support Vector ◽  
Classification Methods ◽  
Multivariate Classification ◽  
Chromatographic Fingerprint ◽  
K Nearest Neighbors ◽  
Pls Discriminant Analysis

Abstract A new analytical method for the differentiation of olive oil from other vegetable oils using reversed-phaseLC and applying chemometric techniques was developed. A 3 cm short column was used to obtain the chromatographic fingerprint of the methyl-transesterified fraction of each vegetable oil. The chromatographic analysis tookonly 4 min. The multivariate classification methods used were k-nearest neighbors, partial least-squares (PLS) discriminant analysis, one-class PLS, support vector machine classification, and soft independent modeling of class analogies. The discrimination of olive oil from other vegetable edible oils was evaluated by several classification quality metrics. Several strategies for the classification of the olive oil wereused: one input-class, two input-class, and pseudo two input-class.

BREAST CANCER DETECTION USING RSFS-BASED FEATURE SELECTION ALGORITHMS IN THERMAL IMAGES

2021 ◽  
pp. 2150020
Author(s):  
Nazila Darabi ◽  
Abdalhossein Rezai ◽  
Seyedeh Shahrbanoo Falahieh Hamidpour
Keyword(s):  
Breast Cancer ◽  
Feature Selection ◽  
Cancer Detection ◽  
Vital Role ◽  
Support Vector ◽  
Computer Aided Detection ◽  
K Nearest Neighbors ◽  
Cad System ◽  
Common Cancer ◽  
Selection Algorithms

Breast cancer is a common cancer in female. Accurate and early detection of breast cancer can play a vital role in treatment. This paper presents and evaluates a thermogram based Computer-Aided Detection (CAD) system for the detection of breast cancer. In this CAD system, the Random Subset Feature Selection (RSFS) algorithm and hybrid of minimum Redundancy Maximum Relevance (mRMR) algorithm and Genetic Algorithm (GA) with RSFS algorithm are utilized for feature selection. In addition, the Support Vector Machine (SVM) and k-Nearest Neighbors (kNN) algorithms are utilized as classifier algorithm. The proposed CAD system is verified using MATLAB 2017 and a dataset that is composed of breast images from 78 patients. The implementation results demonstrate that using RSFS algorithm for feature selection and kNN and SVM algorithms as classifier have accuracy of 85.36% and 75%, and sensitivity of 94.11% and 79.31%, respectively. In addition, using hybrid GA and RSFS algorithm for feature selection and kNN and SVM algorithms as classifier have accuracy of 83.87% and 69.56%, and sensitivity of 96% and 81.81%, respectively, and using hybrid mRMR and RSFS algorithms for feature selection and kNN and SVM algorithms as classifier have accuracy of 77.41% and 73.07%, and sensitivity of 98% and 72.72%, respectively.

Sign in / Sign up

Export Citation Format

Share Document