Search results for: binary classifier

Authors: Abdulaziz Alsadhan, Naveed Khan

Abstract:

In recent years intrusions on computer network are the major security threat. Hence, it is important to impede such intrusions. The hindrance of such intrusions entirely relies on its detection, which is primary concern of any security tool like Intrusion Detection System (IDS). Therefore, it is imperative to accurately detect network attack. Numerous intrusion detection techniques are available but the main issue is their performance. The performance of IDS can be improved by increasing the accurate detection rate and reducing false positive. The existing intrusion detection techniques have the limitation of usage of raw data set for classification. The classifier may get jumble due to redundancy, which results incorrect classification. To minimize this problem, Principle Component Analysis (PCA), Linear Discriminant Analysis (LDA), and Local Binary Pattern (LBP) can be applied to transform raw features into principle features space and select the features based on their sensitivity. Eigen values can be used to determine the sensitivity. To further classify, the selected features greedy search, back elimination, and Particle Swarm Optimization (PSO) can be used to obtain a subset of features with optimal sensitivity and highest discriminatory power. These optimal feature subset used to perform classification. For classification purpose, Support Vector Machine (SVM) and Multilayer Perceptron (MLP) used due to its proven ability in classification. The Knowledge Discovery and Data mining (KDD’99) cup dataset was considered as a benchmark for evaluating security detection mechanisms. The proposed approach can provide an optimal intrusion detection mechanism that outperforms the existing approaches and has the capability to minimize the number of features and maximize the detection rates.

Keywords: Particle Swarm Optimization (PSO), Principle Component Analysis (PCA), Linear Discriminant Analysis (LDA), Local Binary Pattern (LBP), Support Vector Machine (SVM), Multilayer Perceptron (MLP)

Procedia PDF Downloads 337

Authors: Amit Kumar Sinha

Abstract:

A coal preparation plant typically operates with multiple beneficiation circuits to process individual size fractions of coal obtained from mine so that the targeted overall plant efficiency in terms of yield and ash is achieved. Conventional coal beneficiation plant in India or overseas operates generally in two methods of processing; coarse beneficiation with treatment in dense medium cyclones or in baths and fines beneficiation with treatment in flotation cell. This paper seeks to address the proven application of intermediate circuit along with coarse and fines circuit in Jamadoba New Coal Preparation Plant of capacity 2 Mt/y to treat -0.5 mm+0.25 mm size particles in reflux classifier. Previously this size of particles was treated directly in Flotation cell which had operational and metallurgical limitations which will be discussed in brief in this paper. The paper also details test work results performed on the representative samples of TSL coal washeries to determine the top size of intermediate and fines circuit and discusses about the overlapping process of intermediate circuit and how it is process wise suitable to beneficiate misplaced particles from coarse circuit and fines circuit. This paper also compares the separation efficiency (Ep) of various intermediate circuit process equipment and tries to validate the use of reflux classifier over fine coal DMC or spirals. An overview of Modern coal preparation plant treating Indian coal especially Washery Grade IV coal with reference to Jamadoba New Coal Preparation Plant which was commissioned in 2018 with basis of selection of equipment and plant profile, application of reflux classifier in intermediate circuit and process design criteria is also outlined in this paper.

Keywords: intermediate circuit, overlapping process, reflux classifier

Procedia PDF Downloads 107

Authors: M. El Hajji, A. Hallaoui, L. Bazzi, A. Benlhachemi, O. Jbara, A. Tara, B. Bakiz, L. Bazzi, M. Hilali

Abstract:

The objective of this study was the development of zinc-copper binary oxide "Cu2O-ZnO" thin films by the electrochemical method "cathodic electrodeposition" and their uses for the degradation of a basic dye "Congo Red" by direct anodic oxidation. The anode materials synthesized were characterized by X-ray diffraction "XRD" and by scanning electron microscopy "SEM" coupled to EDS.

Keywords: Cu2O-ZnO thin films, cathodic electrodeposition, electrodegradation, Congo Red, BDD

Procedia PDF Downloads 323

Authors: Baljit Singh Khehra, Amar Partap Singh Pharwaha

Abstract:

Clusters of Microcalcifications (MCCs) are most frequent symptoms of Ductal Carcinoma in Situ (DCIS) recognized by mammography. Least-Square Support Vector Machine (LS-SVM) is a variant of the standard SVM. In the paper, LS-SVM is proposed as a classifier for classifying MCCs as benign or malignant based on relevant extracted features from enhanced mammogram. To establish the credibility of LS-SVM classifier for classifying MCCs, a comparative evaluation of the relative performance of LS-SVM classifier for different kernel functions is made. For comparative evaluation, confusion matrix and ROC analysis are used. Experiments are performed on data extracted from mammogram images of DDSM database. A total of 380 suspicious areas are collected, which contain 235 malignant and 145 benign samples, from mammogram images of DDSM database. A set of 50 features is calculated for each suspicious area. After this, an optimal subset of 23 most suitable features is selected from 50 features by Particle Swarm Optimization (PSO). The results of proposed study are quite promising.

Keywords: clusters of microcalcifications, ductal carcinoma in situ, least-square support vector machine, particle swarm optimization

Procedia PDF Downloads 335

Authors: M. Govindarajan

Abstract:

One of the major developments in machine learning in the past decade is the ensemble method, which finds highly accurate classifier by combining many moderately accurate component classifiers. In this research work, new ensemble classification methods are proposed with homogeneous ensemble classifier using bagging and heterogeneous ensemble classifier using arcing and their performances are analyzed in terms of accuracy. A Classifier ensemble is designed using Radial Basis Function (RBF) and Support Vector Machine (SVM) as base classifiers. The feasibility and the benefits of the proposed approaches are demonstrated by the means of standard datasets of intrusion detection. The main originality of the proposed approach is based on three main parts: preprocessing phase, classification phase, and combining phase. A wide range of comparative experiments is conducted for standard datasets of intrusion detection. The performance of the proposed homogeneous and heterogeneous ensemble classifiers are compared to the performance of other standard homogeneous and heterogeneous ensemble methods. The standard homogeneous ensemble methods include Error correcting output codes, Dagging and heterogeneous ensemble methods include majority voting, stacking. The proposed ensemble methods provide significant improvement of accuracy compared to individual classifiers and the proposed bagged RBF and SVM performs significantly better than ECOC and Dagging and the proposed hybrid RBF-SVM performs significantly better than voting and stacking. Also heterogeneous models exhibit better results than homogeneous models for standard datasets of intrusion detection. 

Keywords: data mining, ensemble, radial basis function, support vector machine, accuracy

Procedia PDF Downloads 223

Authors: Wafa' Slaibi Alsharafat

Abstract:

Cloud computing is a modern approach in network environment. According to increased number of network users and online systems, there is a need to help these systems to be away from unauthorized resource access and detect any attempts for privacy contravention. For that purpose, Intrusion Detection System is an effective security mechanism to detect any attempts of attacks for cloud resources and their information. In this paper, Cloud Intrusion Detection System has been proposed in term of reducing or eliminating any attacks. This model concerns about achieving high detection rate after conducting a set of experiments using benchmarks dataset called KDD'99.

Keywords: IDS, cloud computing, anticipating classifier system, intrusion detection

Procedia PDF Downloads 446

Authors: Chang Liu, Nuria Fiol, Isabel Villaescusa, Jordi Poch

Abstract:

Over the last decades, biosorption has been an alternative to costly wastewaters treatment for metal removal. Most of the literature on metal biosorption was devoted to studying of single metal ions but nowadays studies on multi-components biosorption are booming. Hexavalent chromium is usually found in mixtures with divalent metal ions in industries wastewaters. However, studies on the simultaneous removal of Cr(VI) and divalent metals are hardly found and the cooperative or competitive mechanism governing each metal ions sorption is still unclear. In this work, simultaneous sorption of Cr(VI) and Cu(II) from their binary mixtures by using sweet potato vine (SPV) was investigated. Sweet potato is one of the four major grain crops in China. Each year about 2000 tons of SPV are generated as by-products. SPV could be a low-cost biosorbent for metal ions due to its rich in cellulose and lignin. In this work, the sorption of Cr(VI) and Cu(II) from their binary mixtures solutions was studied by using SPV sorbent. Equilibrium studies were carried out in binary mixtures in which Cr(VI) and Cu(II) concentration was both varied between 0.1 mM and 0.3 mM, Cr(VI) and Cu(II) single solutions were also prepared as comparison. All the experiments were performed at pH 3±0.05 under 30±2°C for 7 days to make sure sorption achieved equilibrium. Results showed that (i) chromium was partially (10.93%-42.04%) eliminated under studied conditions through reduction and sorption of hexavalent and trivalent forms. The presence of Cu(II) exerts a synergistic effect on the overall sorption process in all the cases of the 0.1-0.3 mM binary mixtures concentration range. (ii) Cr(VI) removal by SPV is favoured by the presence of Cu(II) in solution, because more protons needed for Cr(VI) reduction are available due to Cu(II)-proton competition; however sorption of the formed Cr(III) is unfavoured as a result of the competition between Cr(III) and Cu(II) for protons and sorbent active sites. (iii) Copper was partially (9.26%-13.91%) sorbed onto SPV under studied conditions. The presence of Cr(VI) in binary mixtures also exerts a synergistic effect on the Cu(II) removal in all the cases of the 0.1-0.3 mM binary mixtures concentration range. The results of the present work indicate that sweet potato vine can be successfully employed for the simultaneously removal of Cr(VI) and Cu(II) in binary mixtures, taking advantage of the synergistic effect provoked by one of the metal ion to each other, even though the acquisition of higher removal yields has to be further investigated. Acknowledgements—This work has been financially supported by Ministry of Human Resources and Social Security of PRC (Anhui15), Education Department of Anhui Province (KJ2016A270) and Anhui Normal University (2015rcpy33, 2014bsqdjj53).

Keywords: sweet potato vine, chromium reduction, divalent metal, synergistic sorption

Procedia PDF Downloads 146

Authors: Khelifi Mustapha, A. Moulay lakhdar, I. Elawady

Abstract:

We will study the unequal error protection for VQ image. We have used the Reed Solomon (RS) Codes as Channel coding because they offer better performance in terms of channel error correction over a binary output channel. One such channel (binary input and output) should be considered if it is the case of the application layer, because it includes all the features of the layers located below and on the what it is usually not feasible to make changes.

Keywords: vector quantization, channel error correction, Reed-Solomon channel coding, application

Procedia PDF Downloads 335

Authors: V. Lokesh, M. Manjunathan, S. Sairam, K. Saithsh Kumar, R. Anantharaj

Abstract:

The densities of pure and its binary mixtures of 1-Butyl-3-methyl imidazolium bis (trifluoro methyl sulfonyl) imide and 1–Ethyl-3-methyl imidazolium ethyl sulphate at different temperature, over the entire composition range were measured at 293.15, 298.15, 303.15, 308.15, 313.15, 318.15, 323.15, 328.15, 33.15, 338.15, 343.15 K. In this study, the liquid-liquid extraction procedure was used. From this experimental data, the excess molar volumes, apparent molar volume, partial molar volumes and the excess partial molar volumes have been calculated for over the whole composition range. Hence, the effect of temperature and composition on all derived thermodynamic properties of this binary mixture will be discussed in terms of intermolecular interactions.

Keywords: ionic liquid, interaction energy, effect of temperature, effect of composition

Procedia PDF Downloads 147

Authors: Végh Ádám, Mekler Csaba, Dezső András, Szabó Dávid, Stomp Dávid, Kaptay György

Abstract:

Grain boundary segregation transition (GBST) has been calculated by a thermodynamic model in binary alloys. The method is used on cementite (Fe3C) segregation in base-centered cubic (ferrite) iron (Fe) in the Fe-C binary system. The GBST line is shown in the Fe3C lacking part of the phase diagram with high solvent (Fe) concentration. At a lower solute content (C) or at higher temperature the grain boundary is composed mostly of the solvent atoms (Fe). On higher concentration compared to the GBST line or at lower temperature a phase transformation occurs at the grain boundary, the latter mostly composed of the associates (Fe3C). These low-segregation and high-segregation states are first order interfacial phase transitions of the grain boundary and can be transformed into each other reversibly. These occur when the GBST line is crossed by changing the bulk composition or temperature.

Keywords: GBST, cementite, segregation, Fe-C alloy

Procedia PDF Downloads 556

Authors: Nikolay Konukhov

Abstract:

This paper to report on a new analytic model for predicting microcontact resistance and the design, fabrication, and testing of microelectromechanical systems (MEMS) metal contact switches with sputtered bimetallic (i.e., gold (Au)-on-Au-platinum (Pt), (Au-on-Au-(6.3at%)Pt)), binary alloy (i.e., Au-palladium (Pd), (Au-(3.7at%)Pd)), and ternary alloy (i.e., Au-Pt-copper (Cu), (Au-(5.0at%)Pt-(0.5at%)Cu)) electric contacts. The microswitches with bimetallic and binary alloy contacts resulted in contact resistance values between 1–2

Keywords: alloys, electric contacts, microelectromechanical systems (MEMS), microswitch

Procedia PDF Downloads 142

Authors: Saba Ebrahimi, Hedieh Ashrafi

Abstract:

Predicting the cover type of forests is a challenge for natural resource managers. In this project, we aim to perform a comprehensive comparative study of two well-known classification methods, support vector machine (SVM) and decision tree (DT). The comparison is first performed among different types of each classifier, and then the best of each classifier will be compared by considering different evaluation metrics. The effect of boosting and bagging for decision trees is also explored. Furthermore, the effect of principal component analysis (PCA) and feature selection is also investigated. During the project, the forest cover-type dataset from the remote sensing and GIS program is used in all computations.

Keywords: classification methods, support vector machine, decision tree, forest cover-type dataset

Procedia PDF Downloads 179

Authors: Wanderson Goncalves e Goncalves, José Alberto Silva de Sá

Abstract:

Human actions are a threat to the balance and conservation of the Amazon forest. Therefore the environmental monitoring services play an important role as the preservation and maintenance of this environment. This study classified forest types using data from a forest inventory provided by the 'Florestal e da Biodiversidade do Estado do Pará' (IDEFLOR-BIO), located between the municipalities of Santarém, Juruti and Aveiro, in the state of Pará, Brazil, covering an area approximately of 600,000 hectares, Bands 3, 4 and 5 of the TM-Landsat satellite image, and Self - Organizing Maps. The information from the satellite images was extracted using QGIS software 2.8.1 Wien and was used as a database for training the neural network. The midpoints of each sample of forest inventory have been linked to images. Later the Digital Numbers of the pixels have been extracted, composing the database that fed the training process and testing of the classifier. The neural network was trained to classify two forest types: Rain Forest of Lowland Emerging Canopy (Dbe) and Rain Forest of Lowland Emerging Canopy plus Open with palm trees (Dbe + Abp) in the Mamuru Arapiuns glebes of Pará State, and the number of examples in the training data set was 400, 200 examples for each class (Dbe and Dbe + Abp), and the size of the test data set was 100, with 50 examples for each class (Dbe and Dbe + Abp). Therefore, total mass of data consisted of 500 examples. The classifier was compiled in Orange Data Mining 2.7 Software and was evaluated in terms of the confusion matrix indicators. The results of the classifier were considered satisfactory, and being obtained values of the global accuracy equal to 89% and Kappa coefficient equal to 78% and F1 score equal to 0,88. It evaluated also the efficiency of the classifier by the ROC plot (receiver operating characteristics), obtaining results close to ideal ratings, showing it to be a very good classifier, and demonstrating the potential of this methodology to provide ecosystem services, particularly in anthropogenic areas in the Amazon.

Keywords: artificial neural network, computational intelligence, pattern recognition, unsupervised learning

Procedia PDF Downloads 337

Authors: Thinh Ngo, Paul Rad, Brian Kelley

Abstract:

Noise estimation is essential in today wireless systems for power control, adaptive modulation, interference suppression and quality of service. Deep learning (DL) has already been applied in the physical layer for modulation and signal classifications. Unacceptably low accuracy of less than 50% is found to undermine traditional application of DL classification for SNR prediction. In this paper, we use divide-and-conquer algorithm and classifier fusion method to simplify SNR classification and therefore enhances DL learning and prediction. Specifically, multiple CNNs are used for classification rather than a single CNN. Each CNN performs a binary classification of a single SNR with two labels: less than, greater than or equal. Together, multiple CNNs are combined to effectively classify over a range of SNR values from −20 ≤ SNR ≤ 32 dB.We use pre-trained CNNs to predict SNR over a wide range of joint channel parameters including multiple Doppler shifts (0, 60, 120 Hz), power-delay profiles, and signal-modulation types (QPSK,16QAM,64-QAM). The approach achieves individual SNR prediction accuracy of 92%, composite accuracy of 70% and prediction convergence one order of magnitude faster than that of traditional estimation.

Keywords: classification, CNN, deep learning, prediction, SNR

Procedia PDF Downloads 101

Authors: Navab Karimi, Tohid Alizadeh

Abstract:

An intelligent vision-based system was designed to measure the quality and purity of raisins. A machine vision setup was utilized to capture the images of bulk raisins in ranges of 5-50% mixed pure-impure berries. The textural features of bulk raisins were extracted using Grey-level Histograms, Co-occurrence Matrix, and Local Binary Pattern (a total of 108 features). Genetic Algorithm and neural network regression were used for selecting and ranking the best features (21 features). As a result, the GLCM features set was found to have the highest accuracy (92.4%) among the other sets. Followingly, multiple feature combinations of the previous stage were fed into the second regression (linear regression) to increase accuracy, wherein a combination of 16 features was found to be the optimum. Finally, a Support Vector Machine (SVM) classifier was used to differentiate the mixtures, producing the best efficiency and accuracy of 96.2% and 97.35%, respectively.

Keywords: sun-dried organic raisin, genetic algorithm, feature extraction, ann regression, linear regression, support vector machine, south azerbaijan.

Procedia PDF Downloads 48

Authors: Kassoul Ilyes

Abstract:

The field of error correcting codes has been revolutionized by the introduction of iteratively decoded codes. Among these, LDPC codes are now a preferred solution thanks to their remarkable performance and low complexity. The binary version of LDPC codes showed even better performance, although it’s decoding introduced greater complexity. This thesis studies the performance of binary LDPC codes using simplified weighted decisions. Information is transported between a transmitter and a receiver by digital transmission systems, either by propagating over a radio channel or also by using a transmission medium such as the transmission line. The purpose of the transmission system is then to carry the information from the transmitter to the receiver as reliably as possible. These codes have not generated enough interest within the coding theory community. This forgetfulness will last until the introduction of Turbo-codes and the iterative principle. Then it was proposed to adopt Pearl's Belief Propagation (BP) algorithm for decoding these codes. Subsequently, Luby introduced irregular LDPC codes characterized by a parity check matrix. And finally, we study simplifications on binary LDPC codes. Thus, we propose a method to make the exact calculation of the APP simpler. This method leads to simplifying the implementation of the system.

Keywords: LDPC, parity check matrix, 5G, BER, SNR

Procedia PDF Downloads 128

Authors: Khadijat T. Bamigbade, Olufade F. W. Onifade

Abstract:

The field of automatic facial expression analysis has been an active research area in the last two decades. Its vast applicability in various domains has drawn so much attention into developing techniques and dataset that mirror real life scenarios. Many techniques such as Local Binary Patterns and its variants (CLBP, LBP-TOP) and lately, deep learning techniques, have been used for facial expression recognition. However, the problem of occlusion has not been sufficiently handled, making their results not applicable in real life situations. This paper develops a simple, yet highly efficient method tagged Local Binary Pattern-Histogram of Gradient (LBP-HOG) with occlusion detection in face image, using a multi-class SVM for Action Unit and in turn expression recognition. Our method was evaluated on three publicly available datasets which are JAFFE, CK, SFEW. Experimental results showed that our approach performed considerably well when compared with state-of-the-art algorithms and gave insight to occlusion detection as a key step to handling expression in wild.

Keywords: automatic facial expression analysis, local binary pattern, LBP-HOG, occlusion detection

Procedia PDF Downloads 139

Authors: Hanjie Xie, Raphael Semiat, Ziyi Zhong

Abstract:

It is well known that many oxidation reactions in nature are closely related to the origin and life activities. One of the features of these natural reactions is that they can proceed under mild conditions employing the oxidant of molecular oxygen (O₂) in the air and enzymes as catalysts. Catalysis is also a necessary part of life for human beings, as many chemical and pharmaceutical industrial processes need to use catalysts. However, most heterogeneous catalytic reactions must be run at high operational reaction temperatures and pressures. It is not strange that, in recent years, research interest has been redirected to green catalysis, e.g., trying to run catalytic reactions under relatively mild conditions as much as possible, which needs to employ green solvents, green oxidants such O₂, particularly air, and novel catalysts. This work reports the efficient binary Fe-Mn metal oxide catalysts for low-temperature formaldehyde (HCHO) oxidation, a toxic pollutant in the air, particularly in indoor environments. We prepared a series of nanosized FeMn oxide catalysts and found that when the molar ratio of Fe/Mn = 1:1, the catalyst exhibited the highest catalytic activity. At room temperature, we realized the complete oxidation of HCHO on this catalyst for 20 h with a high GHSV of 150 L g⁻¹ h⁻¹. After a systematic investigation of the catalyst structure and the reaction, we identified the reaction intermediates, including dioxymethylene, formate, carbonate, etc. It is found that the oxygen vacancies and the derived active oxygen species contributed to this high-low-temperature catalytic activity. These findings deepen the understanding of the catalysis of these binary Fe-Mn metal oxide catalysts.

Keywords: oxygen vacancy, catalytic oxidation, binary transition oxide, formaldehyde

Procedia PDF Downloads 102

Authors: T. Srinivasa Krishna, K. Narendra, K. Thomas, S. S. Raju, B. Munibhadrayya

Abstract:

The densities, speeds of sound and refractive index of the binary mixture of ionic liquid (IL) 1-Butyl-3-methylimidazolium bis(trifluoromethylsulfonyl)imide ([BMIM][Imide]) and Pyrrolidin-2-one(PY) was measured at atmospheric pressure, and over the range of temperatures T= (298.15 -323.15)K. The excess molar volume, excess isentropic compressibility, excess speed of sound, partial molar volumes, and isentropic partial molar compressibility were calculated from the values of the experimental density and speed of sound. From the experimental data excess thermal expansion coefficients and isothermal pressure coefficient of excess molar enthalpy at 298.15K were calculated. The results were analyzed and were discussed from the point of view of structural changes. Excess properties were calculated and correlated by the Redlich–Kister and the Legendre polynomial equation and binary coefficients were obtained. Values of excess partial volumes at infinite dilution for the binary system at different temperatures were calculated from the adjustable parameters obtained from Legendre polynomial and Redlich–Kister smoothing equation. Deviation in refractive indices ΔnD and deviation in molar refraction, ΔRm were calculated from the measured refractive index values. Equations of state and several mixing rules were used to predict refractive indices of the binary mixtures and compared with the experimental values by means of the standard deviation and found to be in excellent agreement. By using Prigogine–Flory–Patterson (PFP) theory, the above thermodynamic mixing functions have been calculated and the results obtained from this theory were compared with experimental results.

Keywords: density, refractive index, speeds of sound, Prigogine-Flory-Patterson theory

Procedia PDF Downloads 378

Authors: Tal Remez, Or Litany, Alex Bronstein

Abstract:

The pursuit of smaller pixel sizes at ever increasing resolution in digital image sensors is mainly driven by the stringent price and form-factor requirements of sensors and optics in the cellular phone market. Recently, Eric Fossum proposed a novel concept of an image sensor with dense sub-diffraction limit one-bit pixels (jots), which can be considered a digital emulation of silver halide photographic film. This idea has been recently embodied as the EPFL Gigavision camera. A major bottleneck in the design of such sensors is the image reconstruction process, producing a continuous high dynamic range image from oversampled binary measurements. The extreme quantization of the Poisson statistics is incompatible with the assumptions of most standard image processing and enhancement frameworks. The recently proposed maximum-likelihood (ML) approach addresses this difficulty, but suffers from image artifacts and has impractically high computational complexity. In this work, we study a variant of a sensor with binary threshold pixels and propose a reconstruction algorithm combining an ML data fitting term with a sparse synthesis prior. We also show an efficient hardware-friendly real-time approximation of this inverse operator. Promising results are shown on synthetic data as well as on HDR data emulated using multiple exposures of a regular CMOS sensor.

Keywords: binary pixels, maximum likelihood, neural networks, sparse coding

Procedia PDF Downloads 172

Authors: Regina Chua

Abstract:

To reduce the costs of re-fielding a large survey, a Random Forest classifier was applied to measure the accuracy of classifying individuals into their assigned segments with the fewest possible questions. Given a long survey, one needed to determine the most predictive ten or fewer questions that would accurately assign new individuals to custom segments. Furthermore, the solution needed to be quick in its classification and usable in non-Python environments. In this paper, a supervised Random Forest classifier was modeled on a dataset with 7,000 individuals, 60 questions, and 254 features. The Random Forest consisted of an iterative collection of individual decision trees that result in a predicted segment with robust precision and recall scores compared to a single tree. A random 70-30 stratified sampling for training the algorithm was used, and accuracy trade-offs at different depths for each segment were identified. Ultimately, the Random Forest classifier performed at 87% accuracy at a depth of 10 with 20 instead of 254 features and 10 instead of 60 questions. With an acceptable accuracy in prioritizing feature selection, new tools were developed for non-Python environments: a worksheet with a formulaic version of the algorithm and an embedded function to predict the segment of an individual in real-time. Random Forest was determined to be an optimal classification model by its feature selection, performance, processing speed, and flexible application in other environments.

Keywords: machine learning, supervised learning, data science, random forest, classification, prediction, predictive modeling

Procedia PDF Downloads 69

Authors: Gajendra Kumar Mourya, Dinesh Bhatia, Akash Handique, Sunita Warjri, Syed Achaab Amir

Abstract:

Nowadays, Medical imaging has become an integral part of modern healthcare. Abdominal CT images are an invaluable mean for abdominal organ investigation and have been widely studied in the recent years. Diagnosis of liver pathologies is one of the major areas of current interests in the field of medical image processing and is still an open problem. To deeply study and diagnose the liver, segmentation of liver is done to identify which part of the liver is mostly affected. Manual segmentation of the liver in CT images is time-consuming and suffers from inter- and intra-observer differences. However, automatic or semi-automatic computer aided segmentation of the Liver is a challenging task due to inter-patient Liver shape and size variability. In this paper, we present a technique for automatic segmenting the liver from CT images using Random Forest Classifier. Random forests or random decision forests are an ensemble learning method for classification that operate by constructing a multitude of decision trees at training time and outputting the class that is the mode of the classes of the individual trees. After comparing with various other techniques, it was found that Random Forest Classifier provide a better segmentation results with respect to accuracy and speed. We have done the validation of our results using various techniques and it shows above 89% accuracy in all the cases.

Keywords: CT images, image validation, random forest, segmentation

Procedia PDF Downloads 282

Authors: Nan Deng, Zhenqiu Liu

Abstract:

Thousands of patients with metastatic tumors were diagnosed with cancers of unknown primary sites each year. The inability to identify the primary cancer site may lead to inappropriate treatment and unexpected prognosis. Nowadays, a large amount of genomics and transcriptomics cancer data has been generated by next-generation sequencing (NGS) technologies, and The Cancer Genome Atlas (TCGA) database has accrued thousands of human cancer tumors and healthy controls, which provides an abundance of resource to differentiate cancer types. Meanwhile, deep convolutional neural networks (CNNs) have shown high accuracy on classification among a large number of image object categories. Here, we utilize 25 cancer primary tumors and 3 normal tissues from TCGA and convert their RNA-Seq gene expression profiling to color images; train, validate and test a CNN classifier directly from these images. The performance result shows that our CNN classifier can archive >80% test accuracy on most of the tumors and normal tissues. Since the gene expression pattern of distant metastases is similar to their primary tumors, the CNN classifier may provide a potential computational strategy on identifying the unknown primary origin of metastatic cancer in order to plan appropriate treatment for patients.

Keywords: bioinformatics, cancer, convolutional neural network, deep leaning, gene expression pattern

Procedia PDF Downloads 266

Authors: F. Jiménez, R. Jódar, M. Martín, G. Sánchez, G. Sciavicco

Abstract:

Abstract—Attribute or feature selection is one of the basic strategies to improve the performances of data classification tasks, and, at the same time, to reduce the complexity of classifiers, and it is a particularly fundamental one when the number of attributes is relatively high. Its application to unsupervised classification is restricted to a limited number of experiments in the literature. Evolutionary computation has already proven itself to be a very effective choice to consistently reduce the number of attributes towards a better classification rate and a simpler semantic interpretation of the inferred classifiers. We present a feature selection wrapper model composed by a multi-objective evolutionary algorithm, the clustering method Expectation-Maximization (EM), and the classifier C4.5 for the unsupervised classification of data extracted from a psychological test named BASC-II (Behavior Assessment System for Children - II ed.) with two objectives: Maximizing the likelihood of the clustering model and maximizing the accuracy of the obtained classifier. We present a methodology to integrate feature selection for unsupervised classification, model evaluation, decision making (to choose the most satisfactory model according to a a posteriori process in a multi-objective context), and testing. We compare the performance of the classifier obtained by the multi-objective evolutionary algorithms ENORA and NSGA-II, and the best solution is then validated by the psychologists that collected the data.

Keywords: evolutionary computation, feature selection, classification, clustering

Procedia PDF Downloads 339

Authors: Onder Yakut, Oguzhan Timus, Emine Dogru Bolat

Abstract:

Health diseases have a vital significance affecting human being's life and life quality. Sudden death events can be prevented owing to early diagnosis and treatment methods. Electrical signals, taken from the human being's body using non-invasive methods and showing the heart activity is called Electrocardiogram (ECG). The ECG signal is used for following daily activity of the heart by clinicians. Heart Rate Variability (HRV) is a physiological parameter giving the variation between the heart beats. ECG data taken from MITBIH Arrhythmia Database is used in the model employed in this study. The detection of arrhythmic heart beats is aimed utilizing the features extracted from the HRV time domain parameters. The developed model provides a satisfactory performance with ~89% accuracy, 91.7 % sensitivity and 85% specificity rates for the detection of arrhythmic beats.

Keywords: arrhythmic beat detection, ECG, HRV, kNN classifier

Procedia PDF Downloads 318

Authors: Elsadig Naseraddeen Ahmed Mohamed

Abstract:

In contrast to the uncertainty and complementary principle, it will be shown in the present paper that the probability of the simultaneous occupation event of any definite values of coordinates by any definite values of momentum and energy at any definite instance of time can be described by a binary definite function equivalent to the difference between their numbers of occupation and evacuation epochs up to that time and also equivalent to the number of exchanges between those occupation and evacuation epochs up to that times modulus two, these binary definite quantities can be defined at all point in the time’s real-line so it form a binary signal represent a complete mechanical description of physical reality, the time of these exchanges represent the boundary of occupation and evacuation epochs from which we can calculate these binary signals using the fact that the time of universe events actually extends in the positive and negative of time’s real-line in one direction of extension when these number of exchanges increase, so there exists noninvertible transformation matrix can be defined as the matrix multiplication of invertible rotation matrix and noninvertible scaling matrix change the direction and magnitude of exchange event vector respectively, these noninvertible transformation will be called actual transformation in contrast to information transformations by which we can navigate the universe’s events transformed by actual transformations backward and forward in time’s real-line, so these information transformations will be derived as an elements of a group can be associated to their corresponded actual transformations. The actual and information model of the universe will be derived by assuming the existence of time instance zero before and at which there is no coordinate occupied by any definite values of momentum and energy, and then after that time, the universe begin its expanding in spacetime, this assumption makes the need for the existence of Laplace’s demon who at one moment can measure the positions and momentums of all constituent particle of the universe and then use the law of classical mechanics to predict all future and past of universe’s events, superfluous, we only need for the establishment of our analog to digital converters to sense the binary signals that determine the boundaries of occupation and evacuation epochs of the definite values of coordinates relative to its origin by the definite values of momentum and energy as present events of the universe from them we can predict approximately in high precision it's past and future events.

Keywords: binary-signal mechanics, actual-information model of the universe, actual-transformation, information-transformation, uncertainty principle, Laplace's demon

Procedia PDF Downloads 142

Authors: Robin C. Ladwig

Abstract:

Diversity Management, as a substantial element of Human Resource Management, aims to secure the economic benefit that assumingly comes with a diverse workforce. Consequently, diversity managers focus on the protection of employees and securing equality measurements to assure organisational gender diversity. Gender diversity as one aspect of Diversity Management seems to adhere to gender binarism and cis-normativity. Workplaces are gendered spaces which are echoing the binary gender-normativity presented in Diversity Management, sold under the label of gender diversity. While the expectation of Diversity Management implies the inclusion of a multiplicity of marginalised groups, such as trans and gender diverse people, in current literature and practice, the reality is curated by gender binarism and cis-normativity. The qualitative multi-method research showed a lack of knowledge about trans and gender diverse matters within the profession of Diversity Management and Human Resources. The semi-structured interviews with trans and gender diverse individuals from various backgrounds and occupations in Australia exposed missing considerations of trans and gender diverse experiences in the inclusivity and gender equity of various workplaces. Even if practitioners consider trans and gender diverse matters under gender diversity, the practical execution is limited to gender binary structures and cis-normative actions as the photo-elicit questionnaire with diversity managers, human resource officers, and personnel management demonstrates. Diversity Management should approach a broader source of informed practice by extending their business focus to the knowledge of humanity studies. Humanity studies could include diversity, queer, or gender studies to increase the inclusivity of marginalised groups such as trans and gender diverse employees and people. Furthermore, the definition of gender diversity should be extended beyond the gender binary and cis-normative experience. People may lose trust in Diversity Management as a supportive ally of marginalised employees if the understanding of inclusivity is limited to a gender binary and cis-normativity value system that misrepresents the richness of gender diversity.

Keywords: cis-normativity, diversity management, gender binarism, trans and gender diversity

Procedia PDF Downloads 166

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

Abstract:

With the popularity of smartphones, mobile apps emerge to meet the diverse needs, however the resources at the disposal are limited, either by the hardware, due to the low computing power, or the software, that does not have the same robustness of desktop environment. For example, in automatic audio classification (AC) tasks, musical information retrieval (MIR) subarea, is required a fast processing and a good success rate. However the mobile platform has limited computing power and the best AC tools are only available for desktop. To solve these problems the fast classifier suits, to mobile environments, the most widespread MIR technologies, seeking a balance in terms of speed and robustness. At the end we found that it is possible to enjoy the best of MIR for mobile environments. This paper presents the results obtained and the difficulties encountered.

Keywords: audio classification, audio extraction, environment mobile, musical information retrieval

Procedia PDF Downloads 510

Authors: Muskan Jain, Baiju Gopal

Abstract:

Objectives: Intimacy in interpersonal relationships is integral to psychological health and everyday wellbeing; the focus is on intimacy, which can be described as feelings of closeness, connection, and belonging within relationships, which is influenced by an individual's gender identity as well as life experiences. The study aims to explore the experiences of intimacy of the non-binary gender; this marginalized community has increased risks of developing the imposter phenomenon. The study explores the influence of IP on the development and sustenance of intimacy in relationships. Methods: The present study accumulates detailed narratives from 10 non-binary young adults ages 18 to 25 in metropolitan cities of India. Thematic analysis was used for the data analysis. Results: Seven major themes have emerged revolving around internalized criticism and self-depreciating behavior, which causes distance between partners. The four themes that result in the internalization of criticism are lack of social stability, invalidation by social units, adverse life experiences, and estrangement due to gender identity. Three themes that encapsulate major difficulties in relationships are limited self-disclosure, inhibition of physical needs, and fear of taking space. The findings have been critically compared and contrasted with the existing body of literature in the domain, which sets the agenda for further inquiry. Conclusion: It is important for future studies to capture the experiences of non-binary genders in India to provide better therapeutic support in order to assist them in forming meaningful and authentic relationships, thus increasing overall wellbeing.

Keywords: imposter phenomenon, intimacy, internalized criticism, marginalized community

Procedia PDF Downloads 36

Authors: Rohit Semwal, Shivam Arora, Saurav, Sangita Roy

Abstract:

This work proposes a supervised framework with deep convolutional neural networks (CNNs) for vision-based sign language recognition of static gestures. Our approach addresses the acquisition and segmentation of correct inputs for the CNN-based classifier. Microsoft Kinect™ sensor, despite complex environmental conditions, can track hands efficiently. Skin Colour based segmentation is applied on cropped images of hands in different poses, used to depict different sign language gestures. The segmented hand images are used as an input for our classifier. The CNN classifier proposed in the paper is able to classify the input images with a high degree of accuracy. The system was trained and tested on 39 static sign language gestures, including 26 letters of the alphabet and 13 commonly used words. This paper includes a problem definition for building the proposed system, which acts as a sign language translator between deaf/mute and the rest of the society. It is then followed by a focus on reviewing existing knowledge in the area and work done by other researchers. It also describes the working principles behind different components of CNNs in brief. The architecture and system design specifications of the proposed system are discussed in the subsequent sections of the paper to give the reader a clear picture of the system in terms of the capability required. The design then gives the top-level details of how the proposed system meets the requirements.

Keywords: sign language, CNN, HCI, segmentation

Procedia PDF Downloads 119