New Set Of Features Research Articles

Fundus Images-Based Detection and Grading of Macular Edema Using Robust Macula Localization

The macula is an oval-shaped area near the center of the human retina, and at its center, there is a small pit known as the fovea. The fovea contains large concentrations of cone cells and is responsible for sharp, colored vision. Macular disorders are the group of diseases that damage the macula, resulting in blurred vision or even blindness. Macular edema (ME), one of the most common types of macular disorder, is caused by fluid accumulation beneath the macula. In this paper, we present an automated system for the detection of ME from fundus images. We introduce a new automated system for the detailed grading of the severity of disease using knowledge of exudates and maculae. A new set of features is used along with a minimum distance classifier for accurate localization of the fovea, which is important for the grading of ME. The proposed system uses different hybrid features and support vector machines for segmentation of exudates. The detailed grading of ME—as both clinically significant ME and non-clinically significant ME—is done using localized foveae and segmented exudates. The proposed algorithm is validated using public and local data sets. We have achieved an average accuracy of 96.1% in the detection and grading of ME with our proposed method.

Improved Protein Phosphorylation Site Prediction by a New Combination of Feature Set and Feature Selection

Phosphorylation of protein is an important post-translational modification that enables activation of various enzymes and receptors included in signaling pathways. To reduce the cost of identifying phosphorylation site by laborious experiments, computational prediction of it has been actively studied. In this study, by adopting a new set of features and applying feature selection by Random Forest with grid search before training by Support Vector Machine, our method achieved better or comparable performance of phosphorylation site prediction for two different data sets.

Supporting Independent Living for Older Adults; Employing a Visual Based Fall Detection Through Analysing the Motion and Shape of the Human Body

Falls are one of the greatest risks for older adults living alone at home. This paper presents a novel visual-based fall detection approach to support independent living for older adults through analysing the motion and shape of the human body. The proposed approach employs a new set of features to detect a fall. Motion information of a segmented silhouette when extracted can provide a useful cue for classifying different behaviours, while variation in shape and the projection histogram can be used to describe human body postures and subsequent fall events. The proposed approach presented here extracts motion information using best-fit approximated ellipse and bounding box around the human body, produces projection histograms and determines the head position over time, to generate 10 features to identify falls. These features are fed into a multilayer perceptron neural network for fall classification. Experimental results show the reliability of the proposed approach with a high fall detection rate of 99.60% and a low false alarm rate of 2.62% when tested with the UR Fall Detection dataset. Comparisons with state of the art fall detection techniques show the robustness of the proposed approach.

On the mathematical modeling of green one-to-one pickup and delivery problem with road segmentation

This paper presents a green one-to-one pickup and delivery problem including a set of new features in the domain of green vehicle routing. The objective here is to enhance the traditional models for the one-to-one pickup and delivery problem by considering several important factors, such as explicit fuel consumption (which can be translated into emissions), variable vehicle speed and road categorization (i.e., urban, non-urban). Accordingly, the paper proposes a mixed integer programming model for the problem. A case study from the Netherlands shows the applicability of the model in practice. The numerical analyses show that the investigated factors has a significant impact on operational-level logistics decisions and the selected key performance indicators. The results suggest that the proposed green model can achieve significant savings in terms of total transportation cost. The total cost reduction is found to be (i) 3.03% by the use of explicit fuel consumption estimation, (ii) up to 10.7% by accounting for variable vehicle speed and (iii) up to 10.5% by considering road categorization. As total cost involves explicit energy usage estimation, the proposed model has potential to offer a better support to aid sustainable logistics decision-making process.

Multifractal detrended fluctuation analysis based novel feature extraction technique for automated detection of focal and non‐focal electroencephalogram signals

In this contribution, a method to segregate electroencephalogram (EEG) signals into focal (F) and non-focal (NF) groups has been proposed, employing a novel multifractal detrended fluctuation analysis (MFDFA)-based feature sets. Manifestations in the fractal behaviour occurring due to the subtle morphological changes in F and NF EEG signals, can serve as an essential presurgical intervention for automated detection of structural epileptogenic area within the human brain. Considering the above-said fact, in the present approach, EEG signals acquired from a publicly available database, are analysed using multifractal parameters to investigate the complex, non-linear and stochastic fluctuations. Based on MFDFA of EEG signals, four statistically significant, new set of features have been extracted, which are eventually being used as inputs to a support vector machines and k-nearest-neighbour classifiers for the purpose of classification of EEG signals. It has been observed that the proposed MFDFA aided feature extraction method delivers quite commensurable and even better results in discriminating F and NF EEG signals, compared with the existing methods studied on the similar database.

Construction and evaluation of the new heuristic malware detection mechanism based on executable files static analysis

The paper presents the application justification of a new set of features collected at the stage of the static analysis of the executable files to address the problem of malicious code detection. In the course of study the following problems were solved: the development of the executable files classifier in the absence of a priori data concerning their functionality; designing the class models of uninfected files and malware during the learning process; the development of malicious code detection procedure using the neural networks mathematical apparatus and decision tree composition relating to the set of features specified on the basis of the executable files static analysis. The paper contains the results of experimental evaluation of the developed detection mechanism efficiency on the basis of neural networks (accuracy was 0.99125) and decision tree composition (accuracy was 0.99240). The obtained data confirmed the hypothesis about the possibility of constructing the heuristic malware analyzer on the basis of features selected during the static analysis of the executable files.

A Machine Learning Approach to Detect Router Advertisement Flooding Attacks in Next-Generation IPv6 Networks

Router advertisement (RA) flooding attack aims to exhaust all node resources, such as CPU and memory, attached to routers on the same link. A biologically inspired machine learning-based approach is proposed in this study to detect RA flooding attacks. The proposed technique exploits information gain ratio (IGR) and principal component analysis (PCA) for feature selection and a support vector machine (SVM)-based predictor model, which can also detect input traffic anomaly. A real benchmark dataset obtained from National Advanced IPv6 Center of Excellence laboratory is used to evaluate the proposed technique. The evaluation process is conducted with two experiments. The first experiment investigates the effect of IGR and PCA feature selection methods to identify the most contributed features for the SVM training model. The second experiment evaluates the capability of SVM to detect RA flooding attacks. The results show that the proposed technique demonstrates excellent detection accuracy and is thus an effective choice for detecting RA flooding attacks. The main contribution of this study is identification of a set of new features that are related to RA flooding attack by utilizing IGR and PCA algorithms. The proposed technique in this paper can effectively detect the presence of RA flooding attack in IPv6 network.

Automatic Classification of Impact Sounds with Rejection of Unknown Samples

The discrimination of very similar sounds is a hard task both for artificial systems and humans. For the former, the main problem lies on finding appropriate features to discriminate each class of sounds, which is an especially hard task when the sounds are very similar, such as impacts on rods of different metals. This paper presents a method to automatically select the features to be used in the classification. Given an initial large set of features, the method measures their discriminative power and builds a reduced set of new features which discriminates the sound classes very accurately. This feature selection method is part of the learning phase of a supervised classification approach also proposed here. In addition, this approach contains a module that rejects unknown sounds also very accurately. This is also an important innovation since most audio classifiers assume all test sounds belong to one of the known classes.

Human Action Recognition Utilizing Variations in Skeleton Dimensions

This paper presents a human action recognition system that distinguishes between different actions using a new set of features based on global variation in the visual appearance of the subject body. The proposed technique utilizes the changes in human body dimensions, during performing an action, to extract this feature set. These dimension variations are calculated from the human body skeleton performing the action to be recognized. The technique can process both 2D and 3D camera videos due to the high-level nature of the extracted features where the skeleton can be extracted from a video captured using traditional 2D cameras or depth sensing cameras. Finally, a multi-class linear support vector machine is employed in the classification stage. Experiments are conducted on Weizmann, Berkeley MHAD, and MSR-Action3D datasets. The results show that the technique achieves an accuracy of 98.9% for Weizmann, 99.63% for Berkeley MHAD, and 94.3% for MSR-Action3D. Moreover, a cross-dataset experiment is held to ensure the generality of the proposed technique, where the system is trained using Berkeley MHAD dataset and tested using MSR-Action3D, which achieved 88.76% accuracy. Moreover, a novel approach for handwriting actions recognition that depends on hands tracking is presented. This approach achieved an accuracy of 100%, and it can be considered an application for the proposed technique.

Rotation invariant wavelet descriptors, a new set of features to enhance plant leaves classification

Automatic plant leaf recognition can play an important role in plant classification due to leaf’s availability, stable features and good potential to discriminate different kinds of species. Amongst many leaf features like leaf venation, margin, texture and lamina, leaf shape is the most important one due to its better discriminative power and ease of analysis. One of the most common leaf shape descriptors is Elliptic Fourier Descriptor (EFD). In this paper a new shape descriptor is introduced as “Rotation Invariant Wavelet Descriptor” (RIWD). The performance of RIWD is compared with IEFD using Flavia dataset. MLP neural network is used as the classifier in this work. Results analysis shows better performance of the proposed feature in classification accuracy. Furthermore, an optimum feature vector is constructed using a set of textural and morphological features and the RIWD that reached 97.5% classification accuracy with low computational cost in comparison with many reported results in Flavia dataset.

Performance Modelling of Planners from Homogeneous Problem Sets

Empirical performance models play an important role in the development of planning portfolios that make a per-domain or per-problem configuration of its search components. Even though such portfolios have shown their power when compared to other systems in current benchmarks, there is no clear evidence that they are capable to differentiate problems (instances) having similar input properties (in terms of objects, goals, etc.) but fairly different runtime for a given planner. In this paper we present a study of empirical performance models that are trained using problems having the same configuration, with the objective of guiding the models to recognize the underlying differences existing among homogeneous problems. In addition we propose a set of new features that boost the prediction capabilities under such scenarios. The results show that the learned models clearly performed over random classifiers, which reinforces the hypothesis that the selection of planners can be done on a per-instance basis when configuring a portfolio.

Determining the optimal features in freezing of gait detection through a single waist accelerometer in home environments

Freezing of gait (FoG) is one of the most disturbing and incapacitating symptoms in Parkinson's disease. It is defined as a sudden block in effective stepping, provoking anxiety, stress and falls. FoG is usually evaluated by means of different questionnaires; however, this method has shown to be not reliable, since it is subjective due to its dependence on patients’ and caregivers’ judgment. Several authors have analyzed the usage of MEMS inertial systems to detect FoG with the aim of objectively evaluating it. So far, specific methods based on accelerometer's frequency response has been employed in many works; nonetheless, since they have been developed and tested in laboratory conditions, their performance is commonly poor when being used at patients’ home. Therefore, this work proposes a new set of features that aims to detect FoG in real environments by using accelerometers. This set of features is compared with three previously reported approaches to detect FoG. The different feature sets are trained by means of several machine learning classifiers; furthermore, different window sizes are also evaluated. In addition, a greedy subset selection process is performed to reduce the computational load of the method and to enable a real-time implementation. Results show that the proposed method detects FoG at patients’ home with 91.7% and 87.4% of sensitivity and specificity, respectively, enhancing the results of former methods between a 5% and 11% and providing a more balanced rate of true positives and true negatives.

Automated Detection of Stereotypical Motor Movements in Autism Spectrum Disorder Using Recurrence Quantification Analysis.

A number of recent studies using accelerometer features as input to machine learning classifiers show promising results for automatically detecting stereotypical motor movements (SMM) in individuals with Autism Spectrum Disorder (ASD). However, replicating these results across different types of accelerometers and their position on the body still remains a challenge. We introduce a new set of features in this domain based on recurrence plot and quantification analyses that are orientation invariant and able to capture non-linear dynamics of SMM. Applying these features to an existing published data set containing acceleration data, we achieve up to 9% average increase in accuracy compared to current state-of-the-art published results. Furthermore, we provide evidence that a single torso sensor can automatically detect multiple types of SMM in ASD, and that our approach allows recognition of SMM with high accuracy in individuals when using a person-independent classifier.

Bispectral features and mean shift clustering for stress and emotion recognition from natural speech

A new set of features and feature enhancement techniques are proposed to recognize emotion and stress from speech signal. The speech waveforms and the glottal waveforms (derived from the recorded emotional/stress speech waveforms) were processed by using third order statistics called bispectrum and 28 (14 from speech waveforms and 14 from glottal waveforms) bispectral based features. In this work, mean shift clustering was used to enhance the discrimination ability of the extracted Bispectral Features (BSFs). Four classifiers were used to distinguish different emotional and stressed states. The performance of the proposed method is tested with three databases. Different experiments were conducted and recognition rates were achieved in the range between 93.44% and 100% for Berlin emotional speech database (BES), between 73.81% and 97.23% for Surrey audio-visual expressed emotion database (SAVEE), between 93.8% and 100% for speech under simulated and actual stress simulated domain (SUSAS) (recognition of multi-style speech under stress-neutral, loud, lombard and anger) and 100% for SUSAS actual domain (recognition of three different levels of stress – high, medium and low). The obtained results indicate that the proposed bispectral based features and mean shift clustering provide promising results to recognize emotion and stress from speech signal.

Performance Evaluation of 5G Millimeter-Wave Cellular Access Networks Using a Capacity-Based Network Deployment Tool

The next fifth generation (5G) of wireless communication networks comes with a set of new features to satisfy the demand of data-intensive applications: millimeter-wave frequencies, massive antenna arrays, beamforming, dense cells, and so forth. In this paper, we investigate the use of beamforming techniques through various architectures and evaluate the performance of 5G wireless access networks, using a capacity-based network deployment tool. This tool is proposed and applied to a realistic area in Ghent, Belgium, to simulate realistic 5G networks that respond to the instantaneous bit rate required by the active users. The results show that, with beamforming, 5G networks require almost 15% more base stations and 4 times less power to provide more capacity to the users and the same coverage performances, in comparison with the 4G reference network. Moreover, they are 3 times more energy efficient than the 4G network and the hybrid beamforming architecture appears to be a suitable architecture for beamforming to be considered when designing a 5G cellular network.

Improved Urban Scene Classification Using Full-Waveform Lidar

Full-waveform lidar data provides supplementary radiometric as well as more accurate geometric target information, when compared to discrete return systems. In this research, a wide range of classes in an urban scene; including trees, medium vegetation, low vegetation (grass), water bodies, pitched roofs, flat roofs, asphalt, vehicles, power lines, walls (fences) and concrete are considered. In order to tackle the challenge of distinguishing geometrically similar classes and enhancing the separability of other targets, a new set of features based on deconvolved waveforms is introduced. The positive effect of the proposed feature dataset on classification accuracy in individual classes is shown using two ensemble classifiers (random forests and RUSBoost). Performance of the classifiers is improved by integration with sampling techniques, especially for the under-represented classes. The final output of the proposed method is a highly detailed land cover map of the urban scene, which affords good separability between critical classes.

Multimodal Omics Data Integration Using Max Relevance--Max Significance Criterion.

This paper presents a novel supervised regularized canonical correlation analysis, termed as CuRSaR, to extract relevant and significant features from multimodal high dimensional omics datasets. The proposed method extracts a new set of features from two multidimensional datasets by maximizing the relevance of extracted features with respect to sample categories and significance among them. It integrates judiciously the merits of regularized canonical correlation analysis (RCCA) and rough hypercuboid approach. An analytical formulation, based on spectral decomposition, is introduced to establish the relation between canonical correlation analysis (CCA) and RCCA. The concept of hypercuboid equivalence partition matrix of rough hypercuboid is used to compute both relevance and significance of a feature. The analytical formulation makes the computational complexity of the proposed algorithm significantly lower than existing methods. The equivalence partition matrix offers an efficient way to find optimum regularization parameters employed in CCA. The superiority of the proposed algorithm over other existing methods, in terms of computational complexity and classification accuracy, is established extensively on real life data.

Text/shape classifier for mobile applications with handwriting input

The paper provides a practical solution to a real-time text/shape differentiation problem for online handwriting input. The proposed structure of the classification system comprises stroke grouping and stroke classification blocks. A new set of features is derived that has low computational complexity. The method achieves 98.5 % text/shape classification accuracy on a benchmark dataset. The proposed stroke grouping machine learning approach improves classification robustness in relation to different input styles. In contrast to the threshold-based techniques, this grouping adaptation enhances the overall discriminating accuracy of the text/shape recognition system by 11.3 %. The solution improves system's response on a touch-screen device.

ASTErIsM: application of topometric clustering algorithms in automatic galaxy detection and classification

We present a study on galaxy detection and shape classification using topometric clustering algorithms. We first use the DBSCAN algorithm to extract, from CCD frames, groups of adjacent pixels with significant fluxes and we then apply the DENCLUE algorithm to separate the contributions of overlapping sources. The DENCLUE separation is based on the localization of pattern of local maxima, through an iterative algorithm which associates each pixel to the closest local maximum. Our main classification goal is to take apart elliptical from spiral galaxies. We introduce new sets of features derived from the computation of geometrical invariant moments of the pixel group shape and from the statistics of the spatial distribution of the DENCLUE local maxima patterns. Ellipticals are characterized by a single group of local maxima, related to the galaxy core, while spiral galaxies have additional ones related to segments of spiral arms. We use two different supervised ensemble classification algorithms, Random Forest, and Gradient Boosting. Using a sample of ~ 24000 galaxies taken from the Galaxy Zoo 2 main sample with spectroscopic redshifts, and we test our classification against the Galaxy Zoo 2 catalog. We find that features extracted from our pipeline give on average an accuracy of ~ 93%, when testing on a test set with a size of 20% of our full data set, with features deriving from the angular distribution of density attractor ranking at the top of the discrimination power.

Automatic defect recognition for pulsed terahertz inspection of basalt fiber reinforced composites

Purpose – The purpose of this paper is to present a system for automatic recognition of defects detected in non-conductive polymer composites using pulsed terahertz imaging. Design/methodology/approach – On the beginning, non-destructive evaluation of composites using electromagnetic waves in terahertz frequency is shortly introduced. Next automatic defects recognition (ADR) algorithm is proposed, focussing on new features calculation. Dimensionality of features space is reduced by using principal component analysis. Finally, results of basalt fiber reinforced composite materials inspection and identification using artificial neural networks is presented and discussed. Findings – It is possible to develop ADR system for non-destructive evaluation of dielectric materials using pulsed terahertz technique. New set of features in time and frequency domains is proposed and verified. Originality/value – ADR in non-destructive testing is utilized in case of digital radiography and ultrasonic testing. Terahertz inspection with pulsed excitation is reported as a source of many useful information about the internal structure of the dielectric material. Up to now ADR based on terahertz non-destructive evaluation systems was not utilized.