Identification of cancerous gene groups from microarray data by employing adaptive genetic and support vector machine technique

Background/Objective: The objective is to minimize ambiguous test cases by using Adaptive Genetic Algorithm (AGA). Problem description/Proposed Method: Here we are concerned with the problem of randomly generated test cases. It can contain some ambiguous test cases, which lead to problems at the organizational level. A random algorithm will generate random test cases each time it is run, and it will have resemblance each time. Another problem related to random algorithms is that running them can take a lot of time. To minimize these issues we propose a new technique, which will reduce the given drawbacks. We proposed an Adaptive Genetic Algorithm (AGA), which will provide legal input in each case where it applied. Thus the problem of ambiguity will decrease. Results/Findings: In this research, the near optimal inputs will be generated based on the Adaptive Genetic Algorithm (AGA), which will reduce the illegal inputs. The fault detection rate is used as the fitness function in AGA. To remove the fault proneness, our AGA uses the coverage metrics of the test cases. Conclusion: Random algorithms will generate low cost test cases in large number but problem is that it will consists ambiguous test cases ,to reduce these here we are using AGA which will further reduce test cases by moderating the illegal inputs.

Water is an important natural resource in our daily life. Water resources play a major role in sustainable development. Surveying and continuous monitoring of water bodies in a vast area is a tedious and timeconsuming task by conventional surveying techniques. Keeping track of changes in the areas of waterbodies due to urbanization and industrialization is very important. The present study aims at determining the spatiotemporal changes in the water bodies from 2008 to 2018 in the drought-hit area of Mahbubnagar, Telangana using satellite-derived spectral index namely,Modified Normalized Difference Water Index (MNDWI) and Support Vector Machine (SVM) technique using Resourcesat-1 Data. Extraction of water bodies using MNDWI and SVM can be done very easily with very little effort as compared to conventional surveying techniques. Using the MNDWI technique,the total area of waterbodies is 322.64 square kilometers in the year 2008 and 362.61 square kilometers in the year 2018. Using the SVM technique, the area of waterbodies is 368.17 square kilometers in the year 2008 and 395.72 in the year 2018. The kappa index values of 2018 by MNDWI technique and SVM technique are 0.86 and 0.91 respectively. The kappa index values of 2008 by MNDWI technique and SVM technique are 0.85 and 0.89 respectively. It is observed that the SVM technique is more accurate than the MNDWI technique. The area of water bodies has increased during the study period mainly due to increased awareness among the public on the importance of water and also initiatives taken by the Government of Telangana, like Mission Kakatiya for the revival of water bodies in the study area.

In order to detect human operator performance degradation or breakdown, this paper proposes an adaptive support vector machine-based method to classify operator mental workload (MWL) into few discrete levels based on psychophysiological measures. Electroencephalogram, electrocardiogram, and electrooculography signals were recorded continuously while the operator was performing safety-critical process control operations in a simulated human-machine system. In coarse-grained analysis, the adaptive exponential smoothing (AES) technique is used to smooth the psychophysiological data and to remove strong artifacts without requiring templates. The MWL level is classified every 30 s by using bounded support vector machine (BSVM) and tenfold cross-validation techniques. Locality preservation projection (LPP) technique is utilized to derive salient psychophysiological features by means of feature reduction. By combining the AES-LPP and BSVM methods, the accuracy of the coarse-grained MWL classification was significantly improved by 11-13%. On the other hand, to perform MWL classification with higher temporal resolution and cross-subject and cross-trial generalizability, finer-grained data analysis is also conducted to recognize MWL levels every 5 s based on a combination of adaptive BSVM (ABSVM) and AES techniques. In comparison with the use of the BSVM algorithm alone, a significant performance improvement by 10-20% is achieved by using the AES-ABSVM method in the finer-grained MWL classification.

With the increase of the hidden layer, the weight update of the LSTM neural network model depends heavily on the gradient descent algorithm, and the convergence speed is slow, resulting in the local extremum of the weight adjustment, which affects the prediction performance of the model. Based on this, this paper proposes an optimized LSTM neural network model based on adaptive genetic algorithm (AGA-LSTM). In this model, the mean squared error is designed as the fitness function, and the adaptive genetic algorithm (AGA) is used to globally optimize the weights between neuron nodes of the LSTM model to improve the generalization ability. The experimental results show that, on the UCI dataset, the prediction accuracy of the AGA-LSTM model is greatly improved compared to the standard LSTM model, which verifies the rationality of the model.

Cancer is the most common disease to threaten human health. The ability to screen individuals with malignant tumours with only a blood sample would be greatly advantageous to early diagnosis and intervention. This study explores the possibility of discriminating between cancer patients and normal subjects with serum surface-enhanced Raman spectroscopy (SERS) and a support vector machine (SVM) through a peripheral blood sample. A total of 130 blood samples were obtained from patients with liver cancer, colonic cancer, esophageal cancer, nasopharyngeal cancer, gastric cancer, as well as 113 blood samples from normal volunteers. Several diagnostic models were built with the serum SERS spectra using SVM and principal component analysis (PCA) techniques. The results show that a diagnostic accuracy of 85.5% is acquired with a PCA algorithm, while a diagnostic accuracy of 95.8% is obtained using radial basis function (RBF), PCA–SVM methods. The results prove that a RBF kernel PCA–SVM technique is superior to PCA and conventional SVM (C-SVM) algorithms in classification serum SERS spectra. The study demonstrates that serum SERS, in combination with SVM techniques, has great potential for screening cancerous patients with any solid malignant tumour through a peripheral blood sample.

This paper presents a combined Entropy Decomposition and Support Vector Machine (EDSVM) technique for Synthetic Aperture Radar (SAR) image classification with the application on rice monitoring. The objective of this paper is to assess the use of multi-temporal data for the supervised classification of rice planting area based on different schedules. Since adequate priori information is needed for this supervised classification, ground truth measurements of rice fields were conducted at Sungai Burung, Selangor, Malaysia for an entire season from the early vegetative stage of the plants to the ripening stage. The theoretical results of Radiative Transfer Theory based on the ground truth parameters are used to de. ne training sets of the different rice planting schedules in the feature space of Entropy Decomposition. The Support Vector Machine is then applied to the feature space to perform the image classification. The effectiveness of this algorithm is demonstrated using multi-temporal RADARSAT-1 data. The results are also used for comparison with the results based on information of training sets from the image using Maximum Likelihood technique, Entropy Decomposition technique and Support Vector Machine technique. The proposed method of EDSVM has shown to be useful in retrieving polarimetric information for each class and it gives a good separation between classes. It not only gives significant results on the classification, but also extends the application of Entropy Decomposition to cover multi-temporal data. Furthermore, the proposed method offers the ability to analyze single-polarized, multi-temporal data with the advantage of the unique features from the combined method of Entropy Decomposition and Support Vector Machine which previously only applicable to multi-polarized data. Classification based on theoretical modeling is also one of the key components in this proposed method where the results from the theoretical models can be applied as the input of the proposed method in order to de. ne the training sets.

Increasing the accuracy of thematic maps generated using satellite imagery is a crucial task in remote sensing. In this study, a product-level fusion (PLF) approach based on integration of different land-type maps generated using various satellite-derived indices including normalized difference water index (NDWI), normalized difference built-up index (NDBI), enhanced vegetation index (EVI), and normalized difference vegetation index (NDVI) is proposed to improve the accuracy of land cover mapping. The suitability of the proposed approach for land cover mapping is evaluated in comparison with two high-performance image classification techniques including support vector machine (SVM) and artificial neural network (ANN). The results show that the overall accuracy and kappa values of about 95.95 % and 0.95, 94.91 % and 0.94, and 85.32 % and 0.82 are achieved for the PLF, SVM, and ANN approaches, respectively. The results indicate superiority of the PLF approach than SVM and ANN techniques for land cover classification of Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) imagery, especially for the extraction of forest, rice, and citrus classes. However, SVM technique also provided reliable result for land cover mapping.

As mosquito parasites breed across many parts of the sub-Saharan Africa part of the world, infected cells embrace an unpredictable and erratic life period. Millions of individual parasites have gene expressions. Ribonucleic acid sequencing (RNA-seq) is a popular transcriptional technique that has improved the detection of major genetic probes. The RNA-seq analysis generally requires computational improvements of machine learning techniques since it computes interpretations of gene expressions. For this study, an adaptive genetic algorithm (A-GA) with recursive feature elimination (RFE) (A-GA-RFE) feature selection algorithms was utilized to detect important information from a high-dimensional gene expression malaria vector RNA-seq dataset. Support Vector Machine (SVM) kernels were used as the classification algorithms to evaluate its predictive performances. The feasibility of this study was confirmed by using an RNA-seq dataset from the mosquito Anopheles gambiae. The technique results in related performance had 98.3 and 96.7 % accuracy rates, respectively. HIGHLIGHTS Dimensionality reduction method based of feature selection Classification using Support vector machine Classification of malaria vector dataset using an adaptive GA-RFE-SVM GRAPHICAL ABSTRACT

This article presents the fault diagnosis of the face milling tool using sound signal. During milling, sound signals of the face milling tool under healthy and fault conditions are acquired. Discrete wavelet transform (DWT) features are extracted from the acquired sound signals. The support vector machine (SVM) technique is used to classify the face milling tool conditions using the extracted DWT features. Also, a comparison of classification efficiencies of different classifiers with respect to different features extraction methods is carried out. It is shown that, all extracted DWT features demonstrate better results than those obtained from selected statistical features and empirical mode decomposition features. The SVM technique is the best classifier as it has given an encouraging result in this study when compared to other classifiers, and it has provided 83% classification accuracy for the given experimental conditions and workpiece of steel alloy 42CrMo4. Hence, the SVM method and DWT technique can be put forward for the applications of condition monitoring of the face milling tool with sound signal.

The primary objective of this study is to solve the Vehicle Routing Problem with Stochastic Demands (VRPSD) under restocking policy by using adaptive Genetic Algorithm (GA). The problem of VRPSD is one of the most important and studied combinatorial optimization problems, which finds its application on wide ranges of logistics and transportation area. It is a variant of a Vehicle Routing Problem (VRP). The algorithms for stochastic VRP are considerably more intricate than deterministic VRP and very time consuming. This has led us to explore the used of metaheuristics focusing on the permutation-based GA. The GA is enhanced by automatically adapting the mutation probability to capture dynamic changing in population. The GA becomes a more effective optimizer where the adaptive schemes are depend on population diversity measure. The proposed algorithm is compared with standard GA on a set of randomly generated problems following some discrete probability distributions inspired by real case of VRPSD in solid waste collection in Malaysia. The performances of several types of adaptive mutation probability were also investigated. Experimental results show performance enhancements when adaptive GA is used.

It is now common knowledge that blind search algorithms cannot perform with equal efficiency on all possible optimization problems defined on a domain. This knowledge applies also to Genetic Algorithms when viewed as global and blind optimizers. From this point of view it is necessary to design algorithms capable of adapting their search behavior by making use in a direct fashion of the knowledge pertaining to the search landscape. The paper introduces a novel adaptive Genetic Algorithm where the exploration/exploitation is directly controlled during evolution using a Bayesian decision process. Test cases are analyzed as to how parameters affect the search behavior of the algorithm.

In this paper we propose an adaptive genetic algorithm (AGA) to optimize wind farm layout in order to achieve a highest aggregate wind power conversion efficiency with the presence of wake effect impacts. Instead of using random “crossover” in each iteration as in conventional GA, our proposed adaptive algorithm introduces novel relocation of “bad” turbines so that turbines experiencing worst wake effect impacts in a layout will be relocated to some new and more efficient positions. Therefore each iteration of the AGA can more effectively improve the aggregate wind power conversion efficiency and greatly accelerate the algorithm convergence. We experiment the proposed AGA and compare its performance with conventional GA based on a number of scenarios such as multi-directional wind distribution, offshore and inland wind distribution, with sparse and crowded farm settings. Numerical results verify the effectiveness of the proposed AGA algorithm which is able to locate an optimal layout at a much faster convergence speed and achieve a higher aggregate wind power output from a farm.

A hybrid diagnostic method utilizing Extended Kalman Filter (EKF) and Adaptive Genetic Algorithm (AGA) is presented for performance degradation estimation and sensor anomaly detection of turbofan engine. The EKF is used to estimate engine component performance degradation for gas path fault diagnosis. The AGA is introduced in the integrated architecture and applied for sensor bias detection. The contributions of this work are the comparisons of Kalman Filters (KF)-AGA algorithms and Neural Networks (NN)-AGA algorithms with a unified framework for gas path fault diagnosis. The NN needs to be trained off-line with a large number of prior fault mode data. When new fault mode occurs, estimation accuracy by the NN evidently decreases. However, the application of the Linearized Kalman Filter (LKF) and EKF will not be restricted in such case. The crossover factor and the mutation factor are adapted to the fitness function at each generation in the AGA, and it consumes less time to search for the optimal sensor bias value compared to the Genetic Algorithm (GA). In a word, we conclude that the hybrid EKF-AGA algorithm is the best choice for gas path fault diagnosis of turbofan engine among the algorithms discussed.

Objective: Using methylation characteristics of human genes to construct machine learning predictive models for screening cervical cancer and precancerous lesions. Methods: Human DNA methylation detection was performed on 224 cervical exfoliated cell specimens from the Cancer Hospital of the Chinese Academy of Medical Sciences, Tianjin Central Hospital of Gynecology Obstetrics, Xinmi Maternal and Child Health Hospital of Henan Province, West China Second Affiliated Hospital of Sichuan University, and Heping Hospital Affiliated to Changzhi Medical College collected during April 2014 and March 2015. The hypermethylated gene fragments related to cervical cancer were selected by high-density, high-association, and hypermethylated gene fragment screening and the LASSO regression algorithm. Taking cervical intraepithelial neoplasia grade 2 (CIN2) or more severe lesions as the research outcome, machine learning predictive models based on the random forest (RF), naive Bayes (NB), and support vector machine (SVM) algorithm, respectively, were constructed. A total of 144 outpatient specimens were used as the training set and 80 cervical exfoliated cell specimens from women participating in the cervical cancer screening program were used as the test set to verify the predictive models. Using histological diagnosis results as the gold standard, the detection efficacy for CIN2 or more severe lesions of the three machine learning predictive models were compared with that of the human papilloma virus (HPV) detection and cytological diagnosis. Results: In the training set of 144 cases, there were 34 cases of HPV positivity, with a positive rate of 23.61%. Cytologically, there were 37 cases diagnosed as no intraepithelial lesion or malignancy (NILM), and 107 cases diagnosed as atypical squamous cells of undetermined significance (ASC-US) or above. Histologically, there were 28 cases without cervical intraepithelial neoplasia or benign cervical lesions, 31 cases of CIN1, 18 cases of CIN2, 31 cases of CIN3, and 36 cases of squamous cell carcinoma. Seven hypermethylated gene fragments were selected from 45 genes, and three machine learning prediction models based on the RF, NB, and SVM algorithm, respectively, were constructed. In the validation set of 80 cases, there were 28 cases of HPV positivity, with a positive rate of 35.00%. Cytologically, there were 65 cases diagnosed as NILM and 15 cases as ASC-US or above. Histologically, there were 39 cases without cervical intraepithelial neoplasia or benign cervical lesions, 10 cases of CIN1, 10 cases of CIN2, 11 cases of CIN3, and 10 cases of squamous cell carcinoma. In the validation set, the area under the curve (AUC) values of the RF model, NB model, SVM model, HPV detection, and cytological diagnosis of CIN2 or above were 0.90, 0.88, 0.82, 0.68, and 0.45, respectively. The DeLong test showed that there was no statistically significant difference in the AUC values between the RF, NB, and SVM models (all P＞0.05), and the AUC values of the RF and NB models were higher than that of HPV detection (both P＜0.01), and the AUC values of the RF, NB, and SVM models were higher than that of cytological diagnosis (all P＜0.01). Compared with the NB model, the sensitivity of the RF model was similar (80.65% vs. 77.42%), but the specificity of the NB model was much higher than that of the RF model (93.88% vs. 73.47%). Conclusion: Among the machine learning prediction models for cervical cancer and precancerous lesions constructed based on human DNA methylation, the NB model has good predictive performance for CIN2 and above lesions, and may be used for screening of cervical cancer and precancerous lesions.

Lung Cancer Survivability Prediction based on Performance Using Classification Techniques of Support Vector Machines, C4.5 and Naive Bayes Algorithms for Healthcare Analytics