Search results for: feature fusion

Authors: Ma Lei-Lei, Zhou You

Abstract:

Aiming at the problems of low detection accuracy of deep learning algorithm in traffic sign detection, this paper proposes improved EfficientDet based traffic sign detection algorithm. Multi-head self-attention is introduced in the minimum resolution layer of the backbone of EfficientDet to achieve effective aggregation of local and global depth information, and this study proposes an improved feature fusion pyramid with increased vertical cross-layer connections, which improves the performance of the model while introducing a small amount of complexity, the Balanced L1 Loss is introduced to replace the original regression loss function Smooth L1 Loss, which solves the problem of balance in the loss function. Experimental results show, the algorithm proposed in this study is suitable for the task of traffic sign detection. Compared with other models, the improved EfficientDet has the best detection accuracy. Although the test speed is not completely dominant, it still meets the real-time requirement.

Keywords: convolutional neural network, transformer, feature pyramid networks, loss function

Procedia PDF Downloads 101

Authors: Sangram A. Sathe, Neha A. Madgulkar, Shruti S. Raut, S. P. Wadkar

Abstract:

Transforaminal lumbar interbody fusion (TLIF) surgeries have nowadays became popular for treatment of degenerated spinal disorders. The interbody fusion technique like TLIF maintains load bearing capacity of the spine and a suitable disc height. Currently many techniques have been introduced to cure Spondylolisthesis. This surgery provides greater rehabilitation of degenerative spines. While performing this TLIF surgery existing methods use guideway, which is a troublesome surgery technique as the use of two separate instruments is required to perform this surgery. This paper presents a concept which eliminates the use of guideway. This concept also eliminates problems that occur like reverting the cage. The concept discussed in this paper also gives high accuracy while performing surgery.

Keywords: TLIF, spondylolisthesis, spine, instruments

Procedia PDF Downloads 335

Authors: Amina Sriba

Abstract:

In this work, interactions between the chemical elements forming the passive film of welded austenitic stainless steel during pitting corrosion are studied. We pay special attention to the chemical elements chromium, molybdenum, iron, nickel, and silicon since they make up the passive film that covers the fusion zone's surface in the welded joint. Molybdenum and chromium are typically the two essential components that control the three crucial stages of pit formation. It was found that while the involvement of chromium is more prominent during the propagation of a pit that has already begun, the enrichment of the molybdenum element in the passive film becomes apparent from the first stage of pit initiation. Additionally, during the pitting corrosion process, there was a noticeable fluctuation in the quantities of the produced oxides and hydroxide species from zone to zone. Regarding the formed hydroxide species, we clearly see that Nickel hydroxides are added to those of Chromium to constitute the outer layer in the passive film of the fusion zone sample, compared to the base metal sample, where only Chromium hydroxide formed on its surface during the pitting corrosion process. This reaction is caused by the preferential dissolution of the austenite phase instead of ferrite in the fusion zone.

Keywords: fusion zone, passive film, chemical elements, pit

Procedia PDF Downloads 59

Authors: Mohd Zamri Osman, Mohd Aizaini Maarof, Mohd Foad Rohani

Abstract:

Human skin detection recognized as the primary step in most of the applications such as face detection, illicit image filtering, hand recognition and video surveillance. The performance of any skin detection applications greatly relies on the two components: feature extraction and classification method. Skin color is the most vital information used for skin detection purpose. However, color feature alone sometimes could not handle images with having same color distribution with skin color. A color feature of pixel-based does not eliminate the skin-like color due to the intensity of skin and skin-like color fall under the same distribution. Hence, the statistical color analysis will be exploited such mean and standard deviation as an additional feature to increase the reliability of skin detector. In this paper, we studied the effectiveness of statistical color feature for human skin detection. Furthermore, the paper analyzed the integrated color and texture using eight classifiers with three color spaces of RGB, YCbCr, and HSV. The experimental results show that the integrating statistical feature using Random Forest classifier achieved a significant performance with an F1-score 0.969.

Keywords: color space, neural network, random forest, skin detection, statistical feature

Procedia PDF Downloads 464

Authors: B. S. Harish, M. B. Revanasiddappa

Abstract:

Due to rapid growth of text documents in digital form, automated text classification has become an important research in the last two decades. The major challenge of text document representations are high dimension, sparsity, volume and semantics. Since the terms are only features that can be found in documents, selection of good terms (features) plays an very important role. In text classification, feature selection is a strategy that can be used to improve classification effectiveness, computational efficiency and accuracy. In this paper, we present a quantitative analysis of most widely used feature selection (FS) methods, viz. Term Frequency-Inverse Document Frequency (tf
idf ), Mutual Information (MI), Information Gain (IG), CHISquare (x2), Term Frequency-Relevance Frequency (tf
rf ), Term Strength (TS), Ambiguity Measure (AM) and Symbolic Feature Selection (SFS) to classify text documents. We evaluated all the feature selection methods on standard datasets like 20 Newsgroups, 4 University dataset and Reuters-21578.

Keywords: classifiers, feature selection, text classification

Procedia PDF Downloads 462

Authors: Laicheng Cao, Xiangqian Su, Youxiao Wu

Abstract:

Feature selection is one of the important problems in network security, pattern recognition, data mining and other fields. In order to remove redundant features, effectively improve the detection speed of intrusion detection system, proposes a new feature selection method, which is based on the invasive weed optimization (IWO) algorithm and tabu search algorithm(TS). Use IWO as a global search, tabu search algorithm for local search, to improve the results of IWO algorithm. The experimental results show that the feature selection method can effectively remove the redundant features of network data information in feature selection, reduction time, and to guarantee accurate detection rate, effectively improve the speed of detection system.

Keywords: intrusion detection, feature selection, iwo, tabu search

Procedia PDF Downloads 533

Authors: Kaushal Kishore, Vaibhav Jain, Hrishikesh Jugade, Saurabh Hadas, Manashi Adhikary, Goutam Mukhopadhyay, Sandip Bhattacharyya

Abstract:

Rotary air compressors in air conditioners are used to suck excessive volume of air from the atmosphere in a small space to provide drive to the components attached to them. Hydraulic test is one of the most important methods to decide the suitability of these components for usage. In the present application, projection welding is used to join the hot rolled steel sheets after forming for manufacturing of air compressors. These sheets belong to two different high strength low alloy (HSLA) steel grades. It was observed that one batch of compressors made of a particular grade was cracking from the weld, whereas those made of another grade were passing the hydraulic tests. Cracking was repeatedly observed from the weld location. A detailed comparative study of the compressors which failed and successfully passed pressure tests has been presented. Location of crack initiation was identified to be the interface of fusion zone/heat affected zone. Shear dimples were observed on the fracture surface confirming the ductile mode of failure. Hardness profile across the weld revealed a sharp rise in hardness in the fusion zone. This was attributed to the presence of untempered martensitic lath in the fusion zone. A sharp metallurgical notch existed at the heat affected zone/fusion zone interface due to transition in microstructure from acicular ferrite and bainite in HAZ to untempered martensite in the fusion zone. In contrast, welds which did not fail during the pressure tests showed a smooth hardness profile with no abnormal rise in hardness in the fusion zone. The bainitic microstructure was observed in the fusion zone of successful welds. This difference in microstructural constituents in the fusion zone was attributed to the presence of a small amount of boron (0.002 wt. %) in the sheets which were cracking. Trace amount of boron is known to substantially increase the hardenability of HSLA steel, and cooling rate during resolidification in the fusion zone is sufficient to form martensite. Post-weld heat treatment was recommended to transform untempered martensite to tempered martensite with lower hardness.

Keywords: compressor, cracking, martensite, weld, boron, hardenability, high strength low alloy steel

Procedia PDF Downloads 172

Authors: R. L. Ujjwal, Abhishek Jain

Abstract:

In the field of computer vision, most facial variations such as identity, expression, emotions and gender have been extensively studied. Automatic age estimation has been rarely explored. With age progression of a human, the features of the face changes. This paper is providing a new comparable study of different type of algorithm to feature extraction [Hybrid features using HAAR cascade & HOG features] & classification [KNN & SVM] training dataset. By using these algorithms we are trying to find out one of the best classification algorithms. Same thing we have done on the feature selection part, we extract the feature by using HAAR cascade and HOG. This work will be done in context of age group classification model.

Keywords: computer vision, age group, face detection

Procedia PDF Downloads 372

Authors: Carlos Huertas, Reyes Juarez-Ramirez

Abstract:

Public health is one of the most critical issues today; therefore, there is great interest to improve technologies in the area of diseases detection. With machine learning and feature selection, it has been possible to aid the diagnosis of several diseases such as cancer. In this work, we present an extension to the Heat Map Based Feature Selection algorithm, this modification allows automatic threshold parameter selection that helps to improve the generalization performance of high dimensional data such as mass spectrometry. We have performed a comparison analysis using multiple cancer datasets and compare against the well known Recursive Feature Elimination algorithm and our original proposal, the results show improved classification performance that is very competitive against current techniques.

Keywords: biomarker discovery, cancer, feature selection, mass spectrometry

Procedia PDF Downloads 342

Authors: Youhang Zhou, Weimin Zeng, Qi Xie

Abstract:

Abstract: In order to solve the wear recognition problem of the machine tool guide surface, a new machine tool guide surface recognition method based on the radar-graph barycentre feature is presented in this paper. Firstly, the gray mean value, skewness, projection variance, flat degrees and kurtosis features of the guide surface image data are defined as primary characteristics. Secondly, data Visualization technology based on radar graph is used. The visual barycentre graphical feature is demonstrated based on the radar plot of multi-dimensional data. Thirdly, a classifier based on the support vector machine technology is used, the radar-graph barycentre feature and wear original feature are put into the classifier separately for classification and comparative analysis of classification and experiment results. The calculation and experimental results show that the method based on the radar-graph barycentre feature can detect the guide surface effectively.

Keywords: guide surface, wear defects, feature extraction, data visualization

Procedia PDF Downloads 522

Authors: M. Sari Yilmaz, N. Karamahmut Mermer

Abstract:

Coal fly ash is formed as a solid waste product from the combustion of coal in coal fired power stations. Huge amounts of fly ash are produced globally every year and are predicted to increase. Nowadays, less than half of the fly ash is used as a raw material for cement manufacturing, construction and the rest of it is disposed as a waste causing yet another environmental concern. For this reason, the recycling of this kind of slurries into useful materials is quite important in terms of economical and environmental aspects. The purpose of this study is to evaluate the Orhaneli and Tuncbilek coal fly ashes for utilization in some industrial applications. Therefore the mineralogical and chemical compositions of these fly ashes were analyzed by X-ray fluorescence (XRF) spectroscopy and X-ray diffraction (XRD). The silicon (Si) and aluminum (Al) in the fly ashes were activated by alkali fusion technique with sodium hydroxide. The obtained extracts were analyzed for Si and Al content by inductively coupled plasma optical emission spectrometry (ICP-OES).

Keywords: extraction, fly ash, fusion, XRD

Procedia PDF Downloads 325

Authors: Nishant Rodrigues, Nicole Spanedda, Chilukuri K. Mohan, Arindam Chakraborty

Abstract:

A crucial objective in quantum chemistry is the computation of the energy levels of chemical systems. This task requires electron-repulsion integrals as inputs, and the steep computational cost of evaluating these integrals poses a major numerical challenge in efficient implementation of quantum chemical software. This work presents a moment-based machine-learning approach for the efficient evaluation of electron-repulsion integrals. These integrals were approximated using linear combinations of a small number of moments. Machine learning algorithms were applied to estimate the coefficients in the linear combination. A random forest approach was used to identify promising features using a recursive feature elimination approach, which performed best for learning the sign of each coefficient but not the magnitude. A neural network with two hidden layers were then used to learn the coefficient magnitudes along with an iterative feature masking approach to perform input vector compression, identifying a small subset of orbitals whose coefficients are sufficient for the quantum state energy computation. Finally, a small ensemble of neural networks (with a median rule for decision fusion) was shown to improve results when compared to a single network.

Keywords: quantum energy calculations, atomic orbitals, electron-repulsion integrals, ensemble machine learning, random forests, neural networks, feature extraction

Procedia PDF Downloads 120

Authors: Mohammad Abdullah-Al-Wadud

Abstract:

In the current era of automation and artificial intelligence, different systems have been increasingly keeping on depending on decision-making capabilities of machines. Such systems/applications may range from simple classifiers to sophisticated surveillance systems based on traditional sensors and related equipment which are becoming more common in the internet of things (IoT) paradigm. However, the available data for such problems are usually imprecise and incomplete, which leads to uncertainty in decisions made based on traditional probability-based classifiers. This requires a robust fusion framework to combine the available information sources with some degree of certainty. The theory of evidence can provide with such a method for combining evidence from different (may be unreliable) sources/observers. This talk will address the employment of the Dempster-Shafer Theory of evidence in some practical applications.

Keywords: decision making, dempster-shafer theory, evidence fusion, incomplete data, uncertainty

Procedia PDF Downloads 430

Authors: Bang Haeyong

Abstract:

Purpose: The objectives of this study were to determine the prevalence, incidence, and risk factors for postoperative fever after lumbar fusion. Methods: This study was a retrospective chart review of 291 patients who underwent lumbar fusion between March 2015 and February 2016 at the Asan Medical Center. Information was extracted from electronic medical records. Postoperative fever was measured at Tmax > 37.7 ℃ and Tmax > 38.3 ℃. The presence of postoperative fever, blood culture, urinary excretion, and/or chest x-ray were evaluated. Patients were evaluated for infection after lumbar fusion. Results: We found 222 patients (76.3%) had a postoperative temperature of 37.7 ℃, and 162 patients (55.7%) had a postoperative temperature of 38.3 ℃ or higher. The percentage of febrile patients trended down following the mean 1.8days (from the first postoperative day to seventh postoperative day). Infection rate was 9 patients (3.1%), respiratory virus (1.7%), urinary tract infection (0.3%), phlebitis (0.3%), and surgical site infection (1.4%). There was no correlation between Tmax > 37.7℃ or Tmax > 38.3℃, and timing of fever, positive blood or urine cultures, pneumonia, or surgical site infection. Risk factors for increased postoperative fever following surgery were confirmed to be delay of defecation (OR=1.37, p=.046), and shorten of remove drainage (OR=0.66, p=.037). Conclusions: The incidence of fever was 76.3% after lumbar fusion and the drainage time was faster in the case of fever. It was thought that the bleeding was absorbed at the operation site and fever occurred. The prevalence of febrile septicemia was higher in patients with long bowel movements before surgery than after surgery. Clinical symptoms should be considered because postoperative fever cannot be determined by fever alone because fever and infection are not significant.

Keywords: lumbar surgery, fever, postoperative, risk factor

Procedia PDF Downloads 251

Authors: Guoliang Lu, Changhou Lu, Xueyong Li

Abstract:

In action recognition, previous studies have demonstrated the effectiveness of using multiple features to improve the recognition performance. We focus on two practical issues: i) most studies use a direct way of concatenating/accumulating multi features to evaluate the similarity between two actions. This way could be too strong since each kind of feature can include different dimensions, quantities, etc; ii) in many studies, the employed classification methods lack of a flexible and effective mechanism to add new feature(s) into classification. In this paper, we explore an unified scheme based on recently-proposed multi-dimensional dynamic time warping (MD-DTW). Experiments demonstrated the scheme's effectiveness of combining multi-feature and the flexibility of adding new feature(s) to increase the recognition performance. In addition, the explored scheme also provides us an open architecture for using new advanced classification methods in the future to enhance action recognition.

Keywords: action recognition, multi features, dynamic time warping, feature combination

Procedia PDF Downloads 441

Authors: Ahmed Ashit

Abstract:

Image fusion is a significant and efficient image processing method used for detecting different types of tumors. This method has been used as an effective combination technique for obtaining high quality images that combine anatomy and physiology of an organ. It is the main key in the huge biomedical machines for diagnosing cancer such as PET-CT machine. This thesis aims to develop an image analysis system for the detection of the eye tumor. Different image processing methods are used to extract the tumor and then mark it on the original image. The images are first smoothed using median filtering. The background of the image is subtracted, to be then added to the original, results in a brighter area of interest or tumor area. The images are adjusted in order to increase the intensity of their pixels which lead to clearer and brighter images. once the images are enhanced, the edges of the images are detected using canny operators results in a segmented image comprises only of the pupil and the tumor for the abnormal images, and the pupil only for the normal images that have no tumor. The images of normal and abnormal images are collected from two sources: “Miles Research” and “Eye Cancer”. The computerized experimental results show that the developed image fusion based eye tumor detection system is capable of detecting the eye tumor and segment it to be superimposed on the original image.

Keywords: image fusion, eye tumor, canny operators, superimposed

Procedia PDF Downloads 367

Authors: Shahram Payandeh

Abstract:

This paper presents an overview of a model which can be used as a part of a decision support system when fusing information from multiple sensing environment. Data fusion has been widely studied in the past few decades and numerous frameworks have been proposed to facilitate decision making process under uncertainties. Multi-sensor data fusion technology plays an increasingly significant role during people tracking and activity recognition. This paper presents an overview of a quantum model as a part of a decision-making process in the context of multi-sensor data fusion. The paper presents basic definitions and relationships associating the decision-making process and quantum model formulation in the presence of uncertainties.

Keywords: quantum model, sensor space, sensor network, decision support

Procedia PDF Downloads 232

Authors: Luo Jiaoyang, Yu Hongyang

Abstract:

In this paper, we explore a method that can be used in the working scene of intelligent industrial robots to confirm the identity information of operators to ensure that the robot executes instructions in a sufficiently safe environment. This approach uses three information modalities, namely visible light, depth, and sound. We explored a variety of fusion modes for the three modalities and finally used the joint feature learning method to improve the performance of the model in the case of noise compared with the single-modal case, making the maximum noise in the experiment. It can also maintain an accuracy rate of more than 90%.

Keywords: multimodal, kinect, machine learning, distance image

Procedia PDF Downloads 82

Authors: Jianfeng Hu

Abstract:

Personal authentication based on electroencephalography (EEG) signals is one of the important field for the biometric technology. More and more researchers have used EEG signals as data source for biometric. However, there are some disadvantages for biometrics based on EEG signals. The proposed method employs entropy measures for feature extraction from EEG signals. Four type of entropies measures, sample entropy (SE), fuzzy entropy (FE), approximate entropy (AE) and spectral entropy (PE), were deployed as feature set. In a silhouettes calculation, the distance from each data point in a cluster to all another point within the same cluster and to all other data points in the closest cluster are determined. Thus silhouettes provide a measure of how well a data point was classified when it was assigned to a cluster and the separation between them. This feature renders silhouettes potentially well suited for assessing cluster quality in personal authentication methods. In this study, “silhouettes scores” was used for assessing the cluster quality of k-means clustering algorithm is well suited for comparing the performance of each EEG dataset. The main goals of this study are: (1) to represent each target as a tuple of multiple feature sets, (2) to assign a suitable measure to each feature set, (3) to combine different feature sets, (4) to determine the optimal feature weighting. Using precision/recall evaluations, the effectiveness of feature weighting in clustering was analyzed. EEG data from 22 subjects were collected. Results showed that: (1) It is possible to use fewer electrodes (3-4) for personal authentication. (2) There was the difference between each electrode for personal authentication (p<0.01). (3) There is no significant difference for authentication performance among feature sets (except feature PE). Conclusion: The combination of k-means clustering algorithm and silhouette approach proved to be an accurate method for personal authentication based on EEG signals.

Keywords: personal authentication, K-mean clustering, electroencephalogram, EEG, silhouettes

Procedia PDF Downloads 288

Authors: A. Torokhti

Abstract:

A new method of mathematical modeling of the distributed nonlinear system is developed. The system is represented by a combination of the set of spatially distributed sensors and the fusion center. Its mathematical model is obtained from the iterative procedure that converges to the model which is optimal in the sense of minimizing an associated cost function.

Keywords: mathematical modeling, non-linear system, spatially distributed sensors, fusion center

Procedia PDF Downloads 386

Authors: Jun Gil Ahn, Jong Kang Park, Jong Tae Kim

Abstract:

In this paper, we analyze major components of activity recognition (AR) in wearable device with 9-axis sensors and sensor fusion filters. 9-axis sensors commonly include 3-axis accelerometer, 3-axis gyroscope and 3-axis magnetometer. We chose sensor fusion filters as Kalman filter and Direction Cosine Matrix (DCM) filter. We also construct sensor fusion data from each activity sensor data and perform classification by accuracy of AR using Naïve Bayes and SVM. According to the classification results, we observed that the DCM filter and the specific combination of the sensing axes are more effective for AR in wearable devices while classifying walking, running, ascending and descending.

Keywords: accelerometer, activity recognition, directiona cosine matrix filter, gyroscope, Kalman filter, magnetometer

Procedia PDF Downloads 334

Authors: Jyh-Cherng Chen, Yi-Jie Lin

Abstract:

This study tries to reuse the fly ash of municipal solid waste incinerator (MSWI) for the synthesis of zeolites. The fly ashes were treated with NaOH alkali fusion at different temperatures for 40 mins and then synthesized the zeolites with hydrothermal method at 105oC for different operation times. The effects of different operation conditions and the optimum synthesis parameters were explored. The specific surface area, surface morphology, species identification, adsorption capacity, and the reuse potentials of the synthesized zeolites were analyzed and evaluated. Experimental results showed that the optimum operation conditions for the synthesis of zeolite from the mixed fly ash were Si/Al=20, alkali/ash=1.5, alkali fusion reaction with NaOH at 800oC for 40 mins, hydrolysis with L/S=200 at 105oC for 24 hr, and hydrothermal synthesis at 105oC for 48 hr. The largest specific surface area of synthesized zeolite could be increased to 943.05m2/g. The influence of different operation parameters on the synthesis of zeolite from mixed fly ash followed the sequence of Si/Al > hydrolysis L/S> hydrothermal time > alkali fusion temperature > alkali/ash ratio. The XRD patterns of synthesized zeolites were identified to be similar with the ZSM-23 zeolite. The adsorption capacities of synthesized zeolite for pollutants were increased as rising the specific surface area of synthesized zeolite. In summary, MSWI fly ash can be treated and reused to synthesize the zeolite with high specific surface area by the alkali fusion and hydrothermal method. The zeolite can be reuse for the adsorption of various pollutants. They have great potential for development.

Keywords: alkali fusion, hydrothermal, fly ash, zeolite

Procedia PDF Downloads 179

Authors: José A. Menezes, Giordano Cabral, Bruno T. Gomes

Abstract:

Choosing good features is an essential part of machine learning. Recent techniques aim to automate this process. For instance, feature learning intends to learn the transformation of raw data into a useful representation to machine learning tasks. In automatic audio classification tasks, this is interesting since the audio, usually complex information, needs to be transformed into a computationally convenient input to process. Another technique tries to generate features by searching a feature space. Genetic algorithms, for instance, have being used to generate audio features by combining or modifying them. We find this approach particularly interesting and, despite the undeniable advances of feature learning approaches, we wanted to take a step forward in the use of genetic algorithms to find audio features, combining them with more conventional methods, like PCA, and inserting search control mechanisms, such as constraints over a confusion matrix. This work presents the results obtained on particular audio classification problems.

Keywords: feature generation, feature learning, genetic algorithm, music information retrieval

Procedia PDF Downloads 438

Authors: Younies Saeed Hassan Mahmoud, Mai Mabrouk, Elsayed Sallam

Abstract:

Analysing DNA microarray data sets is a great challenge, which faces the bioinformaticians due to the complication of using statistical and machine learning techniques. The challenge will be doubled if the microarray data sets contain missing data, which happens regularly because these techniques cannot deal with missing data. One of the most important data analysis process on the microarray data set is feature selection. This process finds the most important genes that affect certain disease. In this paper, we introduce a technique for imputing the missing data in microarray data sets while performing feature selection.

Keywords: DNA microarray, feature selection, missing data, bioinformatics

Procedia PDF Downloads 575

Authors: Mohamed Alimoussa, Alice Porebski, Nicolas Vandenbroucke, Rachid Oulad Haj Thami, Sana El Fkihi

Abstract:

Color and texture are highly discriminant visual cues that provide an essential information in many types of images. Color texture representation and classification is therefore one of the most challenging problems in computer vision and image processing applications. Color textures can be represented in different color spaces by using multiple image descriptors which generate a high dimensional set of texture features. In order to reduce the dimensionality of the feature set, feature selection techniques can be used. The goal of feature selection is to find a relevant subset from an original feature space that can improve the accuracy and efficiency of a classification algorithm. Traditionally, feature selection is focused on removing irrelevant features, neglecting the possible redundancy between relevant ones. This is why some feature selection approaches prefer to use feature clustering analysis to aid and guide the search. These techniques can be divided into two categories. i) Feature clustering-based ranking algorithm uses feature clustering as an analysis that comes before feature ranking. Indeed, after dividing the feature set into groups, these approaches perform a feature ranking in order to select the most discriminant feature of each group. ii) Feature clustering-based subset search algorithms can use feature clustering following one of three strategies; as an initial step that comes before the search, binded and combined with the search or as the search alternative and replacement. In this paper, we propose a new feature clustering-based sequential selection approach for the purpose of color texture representation and classification. Our approach is a three step algorithm. First, irrelevant features are removed from the feature set thanks to a class-correlation measure. Then, introducing a new automatic feature clustering algorithm, the feature set is divided into several feature clusters. Finally, a sequential search algorithm, based on a filter model and a separability measure, builds a relevant and non redundant feature subset: at each step, a feature is selected and features of the same cluster are removed and thus not considered thereafter. This allows to significantly speed up the selection process since large number of redundant features are eliminated at each step. The proposed algorithm uses the clustering algorithm binded and combined with the search. Experiments using a combination of two well known texture descriptors, namely Haralick features extracted from Reduced Size Chromatic Co-occurence Matrices (RSCCMs) and features extracted from Local Binary patterns (LBP) image histograms, on five color texture data sets, Outex, NewBarktex, Parquet, Stex and USPtex demonstrate the efficiency of our method compared to seven of the state of the art methods in terms of accuracy and computation time.

Keywords: feature selection, color texture classification, feature clustering, color LBP, chromatic cooccurrence matrix

Procedia PDF Downloads 140

Authors: Natasha Petrovska, Mirjana Pavlovic, Maria M. Larrondo-Petrie

Abstract:

Neural stem cells (NSCs) are multi-potent, self-renewing cells that generate new neurons. Three subtypes of NSCs can be separated regarding the stages of NSC lineage: quiescent neural stem cells (qNSCs), activated neural stem cells (aNSCs) and neural progenitor cells (NPCs), but their gene expression signatures are not utterly understood yet. Single-cell examinations have started to elucidate the complex structure of NSC populations. Nevertheless, there is a lack of thorough molecular interpretation of the NSC lineage heterogeneity and an increasing need for tools to analyze and improve the efficiency and correctness of single-cell sequencing data. Feature selection and ordering can identify and classify the gene expression signatures of these subtypes and can discover novel subpopulations during the NSCs activation and differentiation processes. The aim here is to review the implementation of the feature selection technique on NSC subtypes and the classification techniques that have been used for the identification of gene expression signatures.

Keywords: feature selection, feature similarity, neural stem cells, genes, feature selection methods

Procedia PDF Downloads 156

Authors: Shao-Tzu Huang, Chen-Chien Hsu, Wei-Yen Wang

Abstract:

Matching high dimensional features between images is computationally expensive for exhaustive search approaches in computer vision. Although the dimension of the feature can be degraded by simplifying the prior knowledge of homography, matching accuracy may degrade as a tradeoff. In this paper, we present a feature matching method based on k-means algorithm that reduces the matching cost and matches the features between images instead of using a simplified geometric assumption. Experimental results show that the proposed method outperforms the previous linear exhaustive search approaches in terms of the inlier ratio of matched pairs.

Keywords: feature matching, k-means clustering, SIFT, RANSAC

Procedia PDF Downloads 362

Authors: Adem Acır

Abstract:

In this study, time dependent neutronic analysis of incineration of minor actinides of a Laser Fusion Inertial Confinement Fusion Fission Energy (LIFE) engine was performed. The calculations were carried out by using MCNP codes with ENDF/B.VI neutron data library. In the neutronic calculations, TRISO particles fueled with minor actinides with natural lithium coolant were performed. The natural lithium cooled LIFE engine used 10 % TRISO fuel minor actinides composition. Tritium breeding ratios (TBR) and energy multiplication factor (M) burnup values were computed as 1.46 and 3.75, respectively. The reactor operation time was calculated as ~ 21 years. The burnup values were obtained as ~1060 GWD/MT, respectively. As a result, the very higher burnup were achieved of LIFE engine.

Keywords: Monte Carlo, minor actinides, nuclear waste, LIFE engine

Procedia PDF Downloads 293

Authors: Rongbo Shen, Jianhua Yao, Kezhou Yan, Kuan Tian, Cheng Jiang, Ke Zhou

Abstract:

This study proposes a generative adversarial networks (GAN) framework to perform synthetic sampling in feature space, i.e., feature augmentation, to address the class imbalance problem in medical image analysis. A feature extraction network is first trained to convert images into feature space. Then the GAN framework incorporates adversarial learning to train a feature generator for the minority class through playing a minimax game with a discriminator. The feature generator then generates features for minority class from arbitrary latent distributions to balance the data between the majority class and the minority class. Additionally, a data cleaning technique, i.e., Tomek link, is employed to clean up undesirable conflicting features introduced from the feature augmentation and thus establish well-defined class clusters for the training. The experiment section evaluates the proposed method on two medical image analysis tasks, i.e., mass classification on mammogram and cancer metastasis classification on histopathological images. Experimental results suggest that the proposed method obtains superior or comparable performance over the state-of-the-art counterparts. Compared to all counterparts, our proposed method improves more than 1.5 percentage of accuracy.

Keywords: class imbalance, synthetic sampling, feature augmentation, generative adversarial networks, data cleaning

Procedia PDF Downloads 130

Authors: Karam Ignaim, Joao M. Fernandes, Andre L. Ferreira

Abstract:

Mapping the artifacts coming from a set of similar products family developed in an ad-hoc manner to make up the resulting software product line (SPL) plays a key role to maintain the consistency between requirements and code. This paper presents a feature mapping approach that focuses on tracing the artifact coming from the migration process, the current feature model (FM), to the other artifacts of the resulting SPL, the reference architecture, and code. Thus, our approach relates each feature of the current FM to its locations in the implementation code, using the reference architecture as an intermediate artifact (as a centric point) to preserve consistency among them during an SPL evolution. The approach uses a particular artifact (i.e., traceability tree) as a solution for managing the mapping process. Tool support is provided using friendlyMapper. We have evaluated the feature mapping approach and tool support by putting the approach into practice (i.e., conducting a case study) of the automotive domain for Classical Sensor Variants Family at Bosch Car Multimedia S.A. The evaluation reveals that the mapping approach presented by this paper fits the automotive domain.

Keywords: feature location, feature models, mapping, software product lines, traceability

Procedia PDF Downloads 131