Intelligent Feature Selection Research Articles

Intelligent feature selection with modified K-nearest neighbor for kidney transplantation prediction

The prediction of kidney transplantation outcome is an important challenge and does not need emphasis because of the lack of available organs. Graft survival prediction is significant to help physicians to take the right decision and enhance survival rate by changing medical procedure. Also, it helps in the best choice of the existing kidney donor and the immunosuppressive management suitable for a patient. But the exact prediction of the graft survival is still not accurate despite of the advancements in this field. The purpose of our research is to design an intelligent kidney transplantation prediction method to solve the prediction problem by utilizing data mining methods. The novelty of this study is focused in presenting: (a) an integrated prediction method, (b) a new intelligent feature selection method, and (c) a modified K-nearest neighbor. Choosing the proper variables is accomplished by merging three feature selectors. The new proposed feature selection method is accomplished using gain ratio, naïve Bayes, and genetic algorithm. Next, the cleaned dataset is utilized to provide quick and precise outcome throughout a modified K-nearest neighbor classifier. Each stage of this proposed method has been evaluated using intense experiments. Experimental results demonstrate the efficiency of all the steps of the proposed method. Additionally, the proposed method has been evaluated versus latest methods. The results presented that this method outperformed all latest and similar literature methods. This method can as well be employed to other related transplant datasets.

Diagnosis of a dermatological lesion using intelligent feature selection technique

ABSTRACTThe content-based image retrieval (CBIR) in dermatological diagnosis context, the information matching is the major concern in terms of feature vector-based classification. The discrimination of the feature vector leads to better classification as well as retrieval rate. Better retrieval results help the dermatologist to improve the diagnosis. In this paper, we proposed a support vector machine weight map (SVM W-Map)-based feature selection along with multi-class particle swarm optimization (PSO) presented for multi-class dermatological imaging dataset. The performance of the system was tested on a dataset including 1450 images and obtained 99.7% for specificity and 95.89% for sensitivity. The analysis and evaluations of results show that the proposed system has higher diagnosis ability when compared with other works.

The application of artificial intelligence and machine learning to automate Gleason grading: Novel tools to develop next generation risk assessment assays.

170 Background: Postoperative risk assessment remains an important variable in the treatment of prostate cancer (PCA). Advances in genomic risk classifiers have aided clinical-decision making; however, clinical-pathologic variables such as Gleason grade and pathologic stage remain significant comparators for accurate prognostication. We aimed to standardize the descriptive pathology of PCA through automation of Gleason grading with artificial intelligence and image analysis feature selection Methods: Retrospective study using radical prostatectomy (RP) tissue microarrays from Henry Ford Hospital and Roswell Park Cancer Center with 8-year median follow-up. Samples were stained with a multiplex immunofluorescent assay: Androgen Receptor (AR), Ki67, Cytokeratin 18, Cytokeratin 5/6 and Alpha-methylacyl-CoA racemase); imaged with a CRI Nuance FX camera and then analyzed with proprietary software to generate a suite of morphometric - attributes that quantitatively characterize the Gleason spectrum. Derived features were univariately correlated with disease progression using the concordance index (CI) along with the hazards ratio and p-value. Results: Starting with a training cohort of 306 patients and a 15% event rate, MIF PCA images were subjected to a machine learning analysis program which incorporates a graph theory-based approach for characterization of gland / ring fusion and fragmentation of tumor architecture (TA) with biomarker quantitation (BQ) (i.e. AR and Ki67). 19 unique image features with 7 TA and 12 TA+BQ were identified, by univariate CI, all TA features were strongly associated with Gleason grading with CI’s reflecting degree of tumor differentiation (CI 0.29-.33, p-value = 0.005). Four TA+BQ features were selected in a training risk model and effectively replaced the clinical Gleason features. By comparison, dominant RP Gleason had a CI of 0.31. Conclusions: Image-based feature selection guided by principles of machine learning has the potential to automate and replace traditional Gleason grading. Such approaches provide the necessary foundation for next generation risk assessment assays.

Automatic, electrocardiographic-based detection of autonomic arousals and their association with cortical arousals, leg movements, and respiratory events in sleep.

The current definition of sleep arousals neglects to address the diversity of arousals and their systemic cohesion. Autonomic arousals (AA) are autonomic activations often associated with cortical arousals (CA), but they may also occur in relation to a respiratory event, a leg movement event or spontaneously, without any other physiological associations. AA should be acknowledged as essential events to understand and explore the systemic implications of arousals. We developed an automatic AA detection algorithm based on intelligent feature selection and advanced machine learning using the electrocardiogram. The model was trained and tested with respect to CA systematically scored in 258 (181 training size/77 test size) polysomnographic recordings from the Wisconsin Sleep Cohort. A precision value of 0.72 and a sensitivity of 0.63 were achieved when evaluated with respect to CA. Further analysis indicated that 81% of the non-CA-associated AAs were associated with leg movement (38%) or respiratory (43%) events. The presented algorithm shows good performance when considering that more than 80% of the false positives (FP) found by the detection algorithm appeared in relation to either leg movement or respiratory events. This indicates that most FP constitute autonomic activations that are indistinguishable from those with cortical cohesion. The proposed algorithm provides an automatic system trained in a clinical environment, which can be utilized to analyze the systemic and clinical impacts of arousals.

Mining corporate annual reports for intelligent detection of financial statement fraud – A comparative study of machine learning methods

Financial statement fraud has been serious concern for investors, audit firms, government regulators, and other capital market stakeholders. Intelligent financial statement fraud detection systems have therefore been developed to support decision-making of the stakeholders. Fraudulent misrepresentation of financial statements in managerial comments has been noticed in recent studies. As such, the purpose of this study was to examine whether an improved financial fraud detection system could be developed by combining specific features derived from financial information and managerial comments in corporate annual reports. To develop this system, we employed both intelligent feature selection and classification using a wide range of machine learning methods. We found that ensemble methods outperformed the remaining methods in terms of true positive rate (fraudulent firms correctly classified as fraudulent). In contrast, Bayesian belief networks (BBN) performed best on non-fraudulent firms (true negative rate). This finding is important because interpretable ``green flag” values (for which fraud is likely absent) could be derived, providing potential decision support to auditors during client selection or audit planning. We also observe that both financial statements and text in annual reports can be utilised to detect non-fraudulent firms. However, non-annual report data (analysts’ forecasts of revenues and earnings) are necessary to detect fraudulent firms. This finding has important implications for selecting variables when developing early warning systems of financial statement fraud.

An Intelligent Feature Selection and Classification Method Based on Hybrid ABC–SVM

Abstract This paper presents a new approach to feature selection and classifcation based on support vector machine and hybrid artificial bee colony. The approach consists of two stages. At the first stage, this paper presented a hybrid artificial bee colony-based classifier model that combines artificial bee colony to improve classification accuracy with the most superior model parameter and features were selected from the original feature set. The classification accuracy and the feature subset provided by the SVM classifier are both considered to update the food source. Finally, the most superior features and optimal model parameter are fed into SVM to identify different class. The testing results verify the effectiveness of the method in extracting feature subset and pattern classification

A Hybrid Intrusion Detection System Based on Multilayer Artificial Neural Network and Intelligent Feature Selection

Abstract. Increased intrusions into computer networks and cyber-attacks have rendered the immunization of cyberspace one of the most important issues of managers and experts in the recent years. Since cyber-attacks have become more sophisticated and hackers have become more professional, mere use techniques such as firewall, cryptography, biometrics, and antiviruses is not sufficient anymore. Therefore, it is necessary to employ efficient intrusion detection systems. Considering 5 classes of cyber-attacks, a detection intrusion system, of abuse detection type, based on the combination of a multilayer artificial neural network and an intelligent feature selection method was introduced in this research. The research results indicated that the feature selection phase using the proposed method yielded more favorable outcomes than the compared method in terms of the evaluation criteria.

Electrocardiogram based identification using a new effective intelligent selection of fused features

Over the years, the feasibility of using Electrocardiogram (ECG) signal for human identification issue has been investigated, and some methods have been suggested. In this research, a new effective intelligent feature selection method from ECG signals has been proposed. This method is developed in such a way that it is able to select important features that are necessary for identification using analysis of the ECG signals. For this purpose, after ECG signal preprocessing, its characterizing features were extracted and then compressed using the cosine transform. The more effective features in the identification, among the characterizing features, are selected using a combination of the genetic algorithm and artificial neural networks. The proposed method was tested on three public ECG databases, namely, MIT-BIH Arrhythmias Database, MITBIH Normal Sinus Rhythm Database and The European ST-T Database, in order to evaluate the proposed subject identification method on normal ECG signals as well as ECG signals with arrhythmias. Identification rates of 99.89% and 99.84% and 99.99% are obtained for these databases respectively. The proposed algorithm exhibits remarkable identification accuracies not only with normal ECG signals, but also in the presence of various arrhythmias. Simulation results showed that the proposed method despite the low number of selected features has a high performance in identification task.

A new short-term load forecast method based on neuro-evolutionary algorithm and chaotic feature selection

In competitive environment of deregulated electricity market, short-term load forecasting (STLF) is a major discussion for efficient operation of power systems. Therefore, the area of electricity load forecasting is still essential need for more accurate and stable load forecast algorithm. However, the electricity load is a non-linear signal with high degree of volatility. In this paper, a new forecasted method based on neural network (NN) and chaotic intelligent feature selection is presented. The proposed feature selection method selects the best set of candidate input which is used as input data for the forecasted. The theory of phase space reconstruction under Taken’s embedding theorem is used to prepare candidate features. Then, candidate inputs relevance to target value are measured by using correlation analysis. Forecast engine is a multilayer perception layer (MLP) NN with hybrid Levenberg–Marquardt (LM) and Differential Evolutionary (DE) learning algorithm. The proposed STLF is tested on PJM and New England electricity markets and compared with some of recent STLF techniques.

Automated classification of oncoming ground vehicles using acoustic echolocation and supervised machine learning

In order to perform useful tasks, robots must have the ability to notice, recognize, and respond to objects in their environment. This requires the acquisition and synthesis of information from a variety of sensors. Here we focus on acoustic echolocation measurements of approaching vehicles, where an acoustic parametric array propagates an audible signal to the oncoming target and the reflected backscattered signal is recorded using the Microsoft Kinect microphone array. Although useful information about the target is hidden inside the noisy time domain measurements, the Dynamic Wavelet Fingerprint process (DWFP) is used to create a time-frequency representation of the data. Intelligent feature selection allows the creation of a small-dimensional feature vector that best differentiates between vehicle types for use in statistical pattern classification routines. Using experimentally measured data from real vehicles at 50 m, this process is able to correctly classify vehicles into one of five known classes with 94% accuracy. Fully three-dimensional simulations allow us to study the nonlinear beam propagation and interaction with real-world targets to improve classification results.

Intelligent feature selection and classification techniques for intrusion detection in networks: a survey

Rapid growth in the Internet usage and diverse military applications have led researchers to think of intelligent systems that can assist the users and applications in getting the services by delivering required quality of service in networks. Some kinds of intelligent techniques are appropriate for providing security in communication pertaining to distributed environments such as mobile computing, e-commerce, telecommunication, and network management. In this paper, a survey on intelligent techniques for feature selection and classification for intrusion detection in networks based on intelligent software agents, neural networks, genetic algorithms, neuro-genetic algorithms, fuzzy techniques, rough sets, and particle swarm intelligence has been proposed. These techniques have been useful for effectively identifying and preventing network intrusions in order to provide security to the Internet and to enhance the quality of service. In addition to the survey on existing intelligent techniques for intrusion detection systems, two new algorithms namely intelligent rule-based attribute selection algorithm for effective feature selection and intelligent rule-based enhanced multiclass support vector machine have been proposed in this paper.

Multiclass feature selection using computational homology for Lamb wave–based damage characterization

We investigate a new approach for characterizing class separability based on topological measures for use with identifying flaw severity in plates. Multi-mode Lamb waves are propagated across a flat-bottom hole of varying depth. Lamb wave tomography reconstructions are first generated to locate and size the flaw at each depth. As the flaw depth increases, scattering and mode conversion effects dominate the raw time-domain signals, obscuring information about flaw severity. Pattern classification provides an alternate means for processing the ultrasonic waveforms to identify flaw severity. High-dimensional feature spaces are generated from the Lamb wave signals using the dynamic wavelet fingerprinting technique. In order to achieve high classification accuracy, an optimal feature space is required. An intelligent feature selection routine is explored here that identifies favorable class distributions in multidimensional feature spaces using computational homology theory. Betti numbers and formal classification accuracies are calculated for each feature space subset to establish a correlation between the topology of the class distribution and the corresponding classification accuracy.

HCS-Neurons: identifying phenotypic changes in multi-neuron images upon drug treatments of high-content screening

BackgroundHigh-content screening (HCS) has become a powerful tool for drug discovery. However, the discovery of drugs targeting neurons is still hampered by the inability to accurately identify and quantify the phenotypic changes of multiple neurons in a single image (named multi-neuron image) of a high-content screen. Therefore, it is desirable to develop an automated image analysis method for analyzing multi-neuron images.ResultsWe propose an automated analysis method with novel descriptors of neuromorphology features for analyzing HCS-based multi-neuron images, called HCS-neurons. To observe multiple phenotypic changes of neurons, we propose two kinds of descriptors which are neuron feature descriptor (NFD) of 13 neuromorphology features, e.g., neurite length, and generic feature descriptors (GFDs), e.g., Haralick texture. HCS-neurons can 1) automatically extract all quantitative phenotype features in both NFD and GFDs, 2) identify statistically significant phenotypic changes upon drug treatments using ANOVA and regression analysis, and 3) generate an accurate classifier to group neurons treated by different drug concentrations using support vector machine and an intelligent feature selection method. To evaluate HCS-neurons, we treated P19 neurons with nocodazole (a microtubule depolymerizing drug which has been shown to impair neurite development) at six concentrations ranging from 0 to 1000 ng/mL. The experimental results show that all the 13 features of NFD have statistically significant difference with respect to changes in various levels of nocodazole drug concentrations (NDC) and the phenotypic changes of neurites were consistent to the known effect of nocodazole in promoting neurite retraction. Three identified features, total neurite length, average neurite length, and average neurite area were able to achieve an independent test accuracy of 90.28% for the six-dosage classification problem. This NFD module and neuron image datasets are provided as a freely downloadable MatLab project at http://iclab.life.nctu.edu.tw/HCS-Neurons.ConclusionsFew automatic methods focus on analyzing multi-neuron images collected from HCS used in drug discovery. We provided an automatic HCS-based method for generating accurate classifiers to classify neurons based on their phenotypic changes upon drug treatments. The proposed HCS-neurons method is helpful in identifying and classifying chemical or biological molecules that alter the morphology of a group of neurons in HCS.

Prediction of Resting-State EEG Using High-Dimensional Patterns

Prediction of resting-state electroencephalography (EEG) usinghigh-dimensional pattern is a challenge due to the uniqueness of each persons brainwave. This study uses the headache EEG recording as the example, and predicts the informative different states by using an intelligent feature selection method. Vomiting and nausea are usually appeared in headache attacks, andit is sensitive to light, sound, or movement. In this study, we use the EEG recording with four classes (inter-headache, pre-headache, headache and post-headache) as the medical database. This study focuses three merits: First, we establish two balanced datasets which contain 2-class (inter-headache and headache) and 4-class brainwave datasets from the original imbalanced headache database so that there is no bias of the prediction system. The 2-class dataset consists of 22 subjects and 176 trials, and the 4-class dataset consists of 40 subjects and 320 trials. Secondly, we propose an efficient SVM-based method for predicting the headache attacks from the EEGby using an inheritable bi-objective combinatorial genetic algorithm (IBCGA). IBCGA automatically selects important features from the brainwave, and the 2-class prediction accuracy of leave-one-trial-out independenttest is 81.25%. Third, from the analysis of the brain region and channel frequency, the brain region T4 is the most important brain regions and alpha and beta frequencies are the most informative frequencies.

A Genetic Algorithm Based Intuitionistic Fuzzification Technique for Attribute Selection

This paper initiates perceptions and algorithms of feature selection, survey of existing feature selection algorithms and assesses diverse algorithms with a classifying frame based on search approaches, valuation criteria, and provides strategy in selecting feature selection algorithms. A unifying platform is projected to continue our efforts headed for building an incorporated system for intelligent feature selection. Feature selection intends to reduce the dimensionality of patterns for classification by choosing the most informative instead of irrelevant and/or redundant features. In this proposed work Intuitionistic fuzzy based feature clustering is proposed for grouping features based on the degree of membership and degree of indeterminacy among the attributes and clusters. In this proposed work a novel approach which uses an Intuitionistic fuzzy version of k-means has been introduced for grouping interdependent features. Genetic algorithm reinstating which is the variation of traditional genetic algorithm is then applied to appraise whether the measured feature is independent of class labels; hence, it leads to eliminate unrelated clusters to classification process and progress the selection of features. The proposed method achieves improvement on classification accuracy and perhaps to select less number of features which show the way to simplification of learning task to a big extent. The Experiment results have been demonstrated by the good performance and also find good enough subset features of this method on using UCI benchmark datasets that are for data mining methods such as Breast Cancer, Sensor and Iris Records.

A new cascade NN based method to short-term load forecast in deregulated electricity market

Short-term load forecasting (STLF) is a major discussion in efficient operation of power systems. The electricity load is a nonlinear signal with time dependent behavior. The area of electricity load forecasting has still essential need for more accurate and stable load forecast algorithm. To improve the accuracy of prediction, a new hybrid forecast strategy based on cascaded neural network is proposed for STLF. This method is consists of wavelet transform, an intelligent two-stage feature selection, and cascaded neural network. The feature selection is used to remove the irrelevant and redundant inputs. The forecast engine is composed of three cascaded neural network (CNN) structure. This cascaded structure can be efficiently extract input/output mapping function of the nonlinear electricity load data. Adjustable parameters of the intelligent feature selection and CNN is fine-tuned by a kind of cross-validation technique. The proposed STLF is tested on PJM and New York electricity markets. It is concluded from the result, the proposed algorithm is a robust forecast method.

An Intelligent Feature Selection Method Based on the Bacterial Foraging Algorithm

This paper puts forward an agent genetic algorithm based on bacteria foraging strategy (BFOA-L) as the feature selection method. The algorithm introduces the bacteria foraging (BF) behavior, and integrates the neural network and link agent structure to achieve fuzzy logic reasoning, so that the weights with no definite physical meaning in traditional neural network are endowed with the physical meaning of fuzzy logic reasoning parameters. The algorithm can maintain the diversity of the agent, so as to achieve satisfactory global optimization precision. The test result shows that this algorithm has good stability, little time complexity and high recognition accuracy.

Compact cancer biomarkers discovery using a swarm intelligence feature selection algorithm

Abstract Biomarker discovery is a typical application from functional genomics. Due to the large number of genes studied simultaneously in microarray data, feature selection is a key step. Swarm intelligence has emerged as a solution for the feature selection problem. However, swarm intelligence settings for feature selection fail to select small features subsets. We have proposed a swarm intelligence feature selection algorithm based on the initialization and update of only a subset of particles in the swarm. In this study, we tested our algorithm in 11 microarray datasets for brain, leukemia, lung, prostate, and others. We show that the proposed swarm intelligence algorithm successfully increase the classification accuracy and decrease the number of selected features compared to other swarm intelligence methods.

Recognizing household activities from human motion data using active learning and feature selection

The ability to accurately recognize human household activities is an important stepping stone toward creating home living assistance systems in the future. Classifying these activities can be difficult due to noisy sensor data, lack of labeled training samples for rare actions and large individual differences in activity execution. In this article, we present two techniques for improving the supervised classification of human activities from motion data: 1) an active learning framework to improve sample efficiency and 2) intelligent feature selection to reduce training time. We demonstrate our techniques using the CMU Multimodal Activity database.

Effects of Macroeconomic and Firm-Specific Factors on Shareholder Wealth: Some Australian Evidence

In today’s hyper-competitive global market there is an increasing focus on revenue growth. Analogously, shareholders and potential investors are interested in shareholder wealth and are also interested in predicted future growth if they were to invest their funds in a firm. This article expands on previous work that explored the variables that drive company wealth creation in the Miscellaneous Industrials sector of the Australian Stock Market. The authors previously studied how a company’s growth and wealth creation changed in comparison to the changes in the Miscellaneous Industrial index, using traditional and artificial intelligence (AI) feature selection techniques. Multi-domain models were used to reduce the number of variables to a manageable number. The primary aim of this study is to observe the effect of including macroeconomic and firm-specific factors (general market factors) into the multi-domain models. Using these selected variables and factors to explore their abilities to predict out of sample values in shareholder wealth and relative shareholder wealth. They find that the variables selected, linked with the macroeconomic and firm-specific factors improves the understanding of the model. The newly formed multi-domain models are found to be useful to select both shareholder and relative shareholder wealth; however, they were more effective with regards to shareholder wealth. <b>TOPICS:</b>Wealth management, security analysis and valuation, developed, statistical methods