This paper devises a novel technique, namely Squirrel Search Deer Hunting-based deep recurrent neural network (SSDH-based DRNN) for cancer-survival rate prediction using gene expression (GE) data. Initially, the input GE data are transformed using the polynomial kernel data transformation. Then entropy-based Bayesian fuzzy clustering is employed for gene selection. Then, the selected features are strengthened through survival indicators based on time series data features, like simple moving average (SMA) and rate of change. Finally, the survival rate prediction is performed using a deep recurrent neural network (DRNN), in which the training is carried out with squirrel search deer hunting (SSDH). The proposed SSDH algorithm is devised by combining Squirrel Search Algorithm (SSA) and deer hunting optimization algorithm (DHOA). The performance of the proposed methodology is analyzed using Pan-Cancer (PANCAN) dataset with a prediction error of 4.05%, RMSE of 7.58, the accuracy of 90.98%, precision of 90.80%, recall of 92.03% and F1-score of 91.41%. The devised method with higher prediction accuracy and the lower prediction error is employed for the cancer survival prediction of the patients for the cancer prognosis. Besides, it will be helpful for the clinical management of cancer patients.
Text mining refers to the process of extracting the high-quality information from the text. It is broadly used in applications, like text clustering, text categorization, text classification, etc. Recently, the text clustering becomes the facilitating and challenging task used to group the text document. Due to some irrelevant terms and large dimension, the accuracy of text clustering is reduced. In this paper, the semantic word processing and novel Particle Grey Wolf Optimizer (PGWO) is proposed for automatic text clustering. Initially, the text documents are given as input to the pre-processing step which caters the useful keyword for feature extraction and clustering. Then, the resultant keyword is applied to wordnet ontology to find out the synonyms and hyponyms of every keyword. Subsequently, the frequency is determined for every keyword which is used to build the text feature library. Since the text feature library contains the larger dimension, the entropy is utilized to select the most significant feature. Finally, the new algorithm Particle Grey Wolf Optimizer (PGWO) is developed by integrating the particle swarm optimization (PSO) into the grey wolf optimizer (GWO). Thus, the proposed algorithm is used to assign the class labels to generate the different clusters of text documents. The simulation is performed to analyze the performance of the proposed algorithm, and the proposed algorithm is compared with existing algorithms. The proposed method attains the clustering accuracy of 80.36% for 20 Newsgroup dataset and the clustering accuracy of 79.63% for Reuter which ensures the better automatic text clustering.
Through Advanced Persistent Threats (APTs), which can reveal data alteration, destruction, or Denial of Service attacks through the examples of exposed hardware and software, the information technology model advances. Moving Target (MTD) is a promising risk-reduction strategy that primarily relies on APTs by utilizing dynamic and randomization techniques on properties that are collaborated. Although there are various MTD approaches to implement the blind random mutation, it still produces better performance overhead as well as poor defense utility. Additionally, APT is a unique assault strategy that was typically developed by hacking groups to steal data or deactivate systems for enormous originalities and uniform countries. APT is a multi-stage, long-term representative, and it is difficult to identify attacks effectively using an outmoded approach. In this paper, Conditional Dingo Optimization Algorithm Deep Residual Network (CDOA-based DRN) is devised for APT detection. Moreover, correlation Tversky index-based similarity is designed for performing feature fusion. The hybrid optimization algorithm effectively increases the performance and reduces various real-world issues. Testing accuracy, True Positive Rate, and False Positive Rate of the newly developed CDOA-based DRN are 95.43%, 96.34%, and 91.43%, respectively, for better performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.