Search

Prediction of software bugs from process logs, temporal access logs, behavior analysis, etc. requires estimation of a wide variety of high-density feature sets. Extracted feature sets must be able to classify these logs into different bug categories with high accuracy, and low complexity. To perform these tasks, a wide variety of Machine Learning Models (MLMs) are proposed by researchers, and each of them varies in terms of their performancelevel nuances, functional advantages, contextual limitations, and application-specific future scopes. Upon analyzing these characteristics, it was observed that existing models are highly context-specific, and cannot be applied to multidomain bug analysis datasets. Moreover, existing models do not incorporate a dynamic feature selection method, which limits their accuracy performance under multiple bug classification applications. To overcome these issues, this paper proposes design of a novel Ensemble deep learning Classifier with Feature Selection for highefficiency Multidomain Bug Prediction under different use cases. The proposed model improves bug representation performance by combining multiple feature extraction methods, including GWO-based novel feature selection techniques. The ensemble classification model, which combines Deep Random Forest, k Nearest Neighbor, Logistic Regression, Multilayer Perceptron, Support Vector Machine, and 1D Convolutional Neural Network classifiers, achieves higher accuracy, precision, recall, and low delay compared to existing models. The model also shows faster classification speeds than existing models and can be deployed for various real-time applications. This accuracy performance was compared with various state-of-the-art models, and it was observed that the proposed model showcases 4.5% higher accuracy, 3.2% better precision, 3.9% higher recall, and 5.5% faster classification performance, which was possible due to integration of intelligent feature selection process with high efficiency classification models under multidomain scenarios. [ABSTRACT FROM AUTHOR]

Accurate analysis of a person’s mood can assist medical psychiatry personnel to assist and improve personal well-being. In order to determine a person’s mood a wide variety of inputs can be used, these inputs include but are not limited to, the person’s social media patterns, facial patterns, ecommerce buying patterns, etc. Analysis of these patterns individually can assist in development of a moderate accuracy psycho-analysis system. Thus, to improve the accuracy and efficiency of mood analysis, this text proposes a deep learning model based on transfer learning, that combines training information from social media activity, and visual actions in order to analyze the person’s state-of-mind. The proposed model is compared with individual algorithms that detect person’s mood, and an accuracy improvement of 12% was achieved. The model is also compared with similar hybrid algorithms that combine multiple psychiatric ques, and it is observed that the proposed model is 8% more effective than these systems due to incorporation of cross validation and transfer learning. [ABSTRACT FROM AUTHOR]

The availability of low cost and tiny sensor devices have resulted in increased adoption of wireless sensor network (WSN) in various industries and organization. The WSN is expected to play a significant role in future internet based application services. WSN has been adopted in healthcare, disaster management, environment monitoring and so on. The low-cost availability of smart devices has led to increased use of wireless devices such as Bluetooth, Wi-Fi etc. Therefore, cognitive radio network plays a significant role in handling spectrum efficiently. The emerging internet access technology such as 4G and 5G network which is expected to come in near future is going to make cognitive spectrum access more challenging. The existing cognitive radio based WSN is not efficient in utilizing spectrum. They induce high collision due to interference and improper channel state information. To address, this work present an efficient distributed opportunistic spectrum access for wireless sensor network. The channel availability of likelihood distribution is computed using continuous-time Markov chain considering primary transmitting users temporal channel usage channel pattern and spatial distribution. The simulation outcome shows the proposed model achieves significant performance improvement over existing model. The proposed model improves the overall spectrum efficiency of cognitive radio wireless sensor network in terms of throughput, packet transmission and collision. [ABSTRACT FROM AUTHOR]