Number Of Feature Sets Research Articles

A developed ant colony algorithm for cancer molecular subtype classification to reveal the predictive biomarker in the renal cell carcinoma

Background: Recently, researchers have been attracted in identifying the crucial genes related to cancer, which plays important role in cancer diagnosis and treatment. However, in performing the cancer molecular subtype classification task from cancer gene expression data, it is challenging to obtain those significant genes due to the high dimensionality and high noise of data. Moreover, the existing methods always suffer from some issues such as premature convergence. Methods: To address those problems, we propose a new ant colony optimization (ACO) algorithm called DACO to classify the cancer gene expression datasets, identifying the essential genes of different diseases. In DACO, first, we propose the initial pheromone concentration based on the weight ranking vector to accelerate the convergence speed; then, a dynamic pheromone volatility factor is designed to prevent the algorithm from getting stuck in the local optimal solution; finally, the pheromone update rule in the Ant Colony System is employed to update the pheromone globally and locally. To demonstrate the performance of the proposed algorithm in classification, different existing approaches are compared with the proposed algorithm on eight high-dimensional cancer gene expression datasets. Results: The experiment results show that the proposed algorithm performs better than other effective methods in terms of classification accuracy and the number of feature sets. It can be used to address the classification problem effectively. Moreover, a renal cell carcinoma dataset is employed to reveal the biological significance of the proposed algorithm from a number of biological analyses. Conclusion: The results demonstrate that CAPS may play a crucial role in the occurrence and development of renal clear cell carcinoma.

Detection of Anorexic Girls-In Blog Posts Written in Hebrew Using a Combined Heuristic AI and NLP Method

In this study, we aim to detect in social media texts written in Hebrew girls who are suspected of being anorexic. We constructed a dataset containing 100 blog posts written by females who are probably anorexic, and 100 blog posts written by females who are likely to be non-anorexic. The construction of this dataset was supervised and approved by an international expert on anorexia. We tested several text classification (TC) methods, using various feature sets (content-based and style-based), five machine learning (ML) methods, three RNN models, four BERT models, three basic preprocessing methods, three feature filtering methods, and parameter tuning. Several insights were found as follows. A set of 50-word n-grams (mostly word unigrams) given by an expert was found as a good basic detector. A heuristic process based on the random forest ML method has overcome a combinatorial explosion and led to significant improvement over a baseline result at a level of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{P}\,{=}$ </tex-math></inline-formula> .01. Application of an iterative process that tests combinations of “k out of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{n}'$ </tex-math></inline-formula> ” where <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{n}'\,{ &lt; }$ </tex-math></inline-formula> n (n is the number of feature sets) lead to a result of 90.63%, using a combination of 300 features from ten feature sets.

Real‐time approach for oscillatory stability assessment in large‐scale power systems based on MRMR classifier

An integrated approach for real-time oscillatory stability assessment (OSA) based on mutual information theory is proposed in this study. An advanced maximum-relevance minimum-redundancy (MRMR) ensemble scheme is designed to explore the internal relations between operation variables and the oscillatory stability margin (OSM). Multiple MRMR procedures are generated in parallel to select multiple different feature subsets, in which each feature presents a relevant and complementary description of OSM. The functional expression of the relationships is obtained by curve fitting. The 21-bus system and 1648-bus system are implemented to test the performance of the proposed approach. A compared investigation is made with some other data mining methods. The impacts of the number of feature sets, size of feature sets, size of training set, invalid data and computation time are studied. Experimental results reveal that the proposed approach provides faster and more accurate assessment results and is a real-time adaptive approach for OSA.

An optimised approach to detect the identity of hidden information in gray scale and colour images

Feature-based steganalysis is an emerging trend in the domain of Information Forensics, aims to discover the identity of secret information present in the covert communication by analysing the statistical features of cover/stego image. Due to massive volumes of auditing data as well as complex and dynamic behaviours of steganogram features, optimising those features is an important open problem. This paper focused on optimising the number of features using the proposed quick artificial bee colony (qABC) algorithm. Here we tested for three steganalysers, namely subtractive pixel adjacency matrix (SPAM), phase aware projection model (PHARM) and colour filter array (CFA) for the break our steganographic system (BOSS) 1.01 datasets. The significant improvement in the convergence nature of qABC quickly improves the solution and fine tune the search than their real counterparts. The results reveal that qABC method with support vector machine (SVM) classifier outperforms the non-optimised version concerning classification accuracy and reduced number of feature sets.

Hybrid BFO and PSO Swarm Intelligence Approach for Biometric Feature Optimization

Nature-inspired novel swarm intelligence algorithms have gained more proliferation due to a variety of applications and uses in optimization of complex problems and selection of discriminatory sets of features to classify huge datasets during the past few decades. Feature selection is an efficient and useful pre-processing technique for solving classification problems in computer vision, data mining and pattern recognition. The major challenges of solving the feature selection problems lay in swarm intelligence algorithms which are capable of handling the vast number of feature sets from involved databases. In biometric based recognition systems, face recognition is a non-intrusive approach to identify individuals based on their discriminatory sets of facial feature vectors. In this paper, the authors tend to propose a unique novel hybrid based on Bacterial Foraging Optimization (BFO) and Particle swarm optimization (PSO) approach for the selection of best facial feature vectors that enhance the identification accuracy of the individual recognition because concerned facial info will contain useless and redundant face expression. The proposed hybrid approach mitigates irrelevant facial features in the feature space and selects the relevant set of features from the facial feature space. The proposed feature selection approach presents promising experimental results with respect to the number of facial feature subsets. The identification accuracies are superior to other approaches from the literature.

BRAIN TUMOR CLASSIFICATION BASED ON CLUSTERED DISCRETE COSINE TRANSFORM IN COMPRESSED DOMAIN

This study presents a novel method to classify the brain tumors by means of efficient and integrated methods so as to increase the classification accuracy. In conventional systems, the problem being the same to extract the feature sets from the database and classify tumors based on the features sets. The main idea in plethora of earlier researches related to any classification method is to increase the classification accuracy.The actual need is to achieve a better accuracy in classification, by extracting more relevant feature sets after dimensionality reduction. There exists a trade-off between accuracy and the number of feature sets. Hence the focus in this study is to implement Discrete Cosine Transform (DCT) on the brain tumor images for various classes. Using DCT, by itself, it offers a fair dimension reduction in feature sets.Later on, sequentially K-means algorithm is applied on DCT coefficients to cluster the feature sets. These cluster information are considered as refined feature sets and classified using Support Vector Machine (SVM) is proposed in this study. This method of using DCT helps to adjust and vary the performance of classification based on the count of the DCT coefficients taken into account. There exists a good demand for an automatic classification of brain tumors which grealtly helps in the process of diagnosis. In this novel work, an average of 97% and a maximum of 100% classification accuracy has been achieved. This research is basically aiming and opening a new way of classification under compressed domain. Hence this study may be highly suitable for diagnosing under mobile computing and internet based medical diagnosis.

Fused Feature Representation Discovery for High-Dimensional and Sparse Data

The automatic discovery of a significant low-dimensional feature representation from a given data set is a fundamental problem in machine learning. This paper focuses specifically on the development of the feature representation discovery methods appropriate for high-dimensional and sparse data. We formulate our feature representation discovery problem as a variant of the semi-supervised learning problem, namely, as an optimization problem over unsupervised data whose objective is evaluating the impact of each feature with respect to modeling a target task according to the initial model constructed by using supervised data. The most notable characteristic of our method is that it offers a feasible processing speed even if the numbers of data and features are both in the millions or even billions, and successfully provides a significantly small number of feature sets, i.e., fewer than 10, that can also offer improved performance compared with those obtained with the original feature sets. We demonstrate the effectiveness of our method in experiments consisting of two well-studied natural language processing tasks.

Relational Features in Fine-Grained Opinion Analysis

Fine-grained opinion analysis methods often make use of linguistic features but typically do not take the interaction between opinions into account. This article describes a set of experiments that demonstrate that relational features, mainly derived from dependency-syntactic and semantic role structures, can significantly improve the performance of automatic systems for a number of fine-grained opinion analysis tasks: marking up opinion expressions, finding opinion holders, and determining the polarities of opinion expressions. These features make it possible to model the way opinions expressed in natural-language discourse interact in a sentence over arbitrary distances. The use of relations requires us to consider multiple opinions simultaneously, which makes the search for the optimal analysis intractable. However, a reranker can be used as a sufficiently accurate and efficient approximation. A number of feature sets and machine learning approaches for the rerankers are evaluated. For the task of opinion expression extraction, the best model shows a 10-point absolute improvement in soft recall on the MPQA corpus over a conventional sequence labeler based on local contextual features, while precision decreases only slightly. Significant improvements are also seen for the extended tasks where holders and polarities are considered: 10 and 7 points in recall, respectively. In addition, the systems outperform previously published results for unlabeled (6 F-measure points) and polarity-labeled (10–15 points) opinion expression extraction. Finally, as an extrinsic evaluation, the extracted MPQA-style opinion expressions are used in practical opinion mining tasks. In all scenarios considered, the machine learning features derived from the opinion expressions lead to statistically significant improvements.

Modeling listener distraction resulting from audio-on-audio interference

As devices that produce audio become more commonplace and increasingly portable, situations in which two competing audio programs are present occur more regularly. In order to support the design of systems intended to mitigate the effects of interfering audio (including sound field control, noise cancelation or source separation systems), it is desirable to model the perceived distraction in such situations. Distraction ratings were collected for a range of audio-on-audio interference situations including various target and interferer programs at three interferer levels, with and without road noise. Time-frequency target-to-interferer ratio (TIR) maps of the stimuli were created using a simple auditory model. A number of feature sets were extracted from the TIR maps, including combinations of mean, standard deviation, minimum and maximum TIR taken across the duration of the program item. In order to predict distraction ratings from the features, linear regression models were produced. The models were evaluated for goodness-of-fit (RMSE) and generalizability (using a K-fold cross-validation procedure). The best model performed well, with almost all predictions falling within the 95% confidence intervals of the perceptual data. A validation data set was used to test the model, suggesting areas for future improvement.

Classifying human leg motions with uniaxial piezoelectric gyroscopes.

This paper provides a comparative study on the different techniques of classifying human leg motions that are performed using two low-cost uniaxial piezoelectric gyroscopes worn on the leg. A number of feature sets, extracted from the raw inertial sensor data in different ways, are used in the classification process. The classification techniques implemented and compared in this study are: Bayesian decision making (BDM), a rule-based algorithm (RBA) or decision tree, least-squares method (LSM), k-nearest neighbor algorithm (k-NN), dynamic time warping (DTW), support vector machines (SVM), and artificial neural networks (ANN). A performance comparison of these classification techniques is provided in terms of their correct differentiation rates, confusion matrices, computational cost, and training and storage requirements. Three different cross-validation techniques are employed to validate the classifiers. The results indicate that BDM, in general, results in the highest correct classification rate with relatively small computational cost.

A neural network based approach for protein structural class prediction

The paper provides an alternative approach to protein structural class prediction employing artificial neural network. Existing works on protein structural class prediction are computationally intensive. The method employs SOFM for extraction of representative feature vectors, for the four different structural classes and then uses Principal Component Analysis for finding optimum feature vector dimension. Nearest neighborhood classification technique is finally utilised; to classify these protein datapoints to their respective classes. The proposed work presented in this paper, maintains the same level of classification accuracy in minimum computation time, as it employs most prominent and reduced number of feature set for classification.

Superior feature-set ranking for small samples using bolstered error estimation

Ranking feature sets is a key issue for classification, for instance, phenotype classification based on gene expression. Since ranking is often based on error estimation, and error estimators suffer to differing degrees of imprecision in small-sample settings, it is important to choose a computationally feasible error estimator that yields good feature-set ranking. This paper examines the feature-ranking performance of several kinds of error estimators: resubstitution, cross-validation, bootstrap and bolstered error estimation. It does so for three classification rules: linear discriminant analysis, three-nearest-neighbor classification and classification trees. Two measures of performance are considered. One counts the number of the truly best feature sets appearing among the best feature sets discovered by the error estimator and the other computes the mean absolute error between the top ranks of the truly best feature sets and their ranks as given by the error estimator. Our results indicate that bolstering is superior to bootstrap, and bootstrap is better than cross-validation, for discovering top-performing feature sets for classification when using small samples. A key issue is that bolstered error estimation is tens of times faster than bootstrap, and faster than cross-validation, and is therefore feasible for feature-set ranking when the number of feature sets is extremely large.