درخت حوزه‌های تخصصی

In this paper, we have extended our literature survey with experimental implementation. Analyzing numerous Artificial Intelligence (AI) techniques in software engineering (SE) can help understand the field better; the outcomes will be more effective when used with it. Our manuscript shows various AI-based algorithms that include Machine learning techniques (ML), Artificial Neural Networks (ANN), Deep Neural Networks (DNN) and Convolutional Neural Networks (CNN), Natural Language Processing (NLP), Genetic Algorithms (GA) applications. Software testing using Ant Colony Optimization (ACO) approach, predicting software maintainability with Group Method of Data Handling (GMDH), Probabilistic Neural Network (PNN), and Software production with time series analysis technique. Furthermore, data is the fuel for AI-based model testing and validation techniques. We have also used NASA dataset promise repository in our script. There are various applications of AI in SE, and we have experimentally demonstrated one among them, i.e., software defect prediction using AI-based techniques. Moreover, the expected future trends have also been mentioned; these are some significant contributions to the research

Limited energy capacity, physical distance between two nodes and the stochastic link quality are the major parameters in the selection of routing path in the internet of things network. To alleviate the problem of stochastic link quality as channel gain reinforcement based Q-learning energy balanced routing is presented in this paper. Using above mentioned parameter an optimization problem has been formulated termed as reward or utility of network. Further, formulated optimization problem converted into Markov decision problem (MDP) and their state, value, action and reward function are described. Finally, a QRL algorithm is presented and their time complexity is analyses. To show the effectiveness of proposed QRL algorithm extensive simulation is performed in terms of convergence property, energy consumption, residual energy and reward with respect to state-of-art-algorithms.

Introduction: According to the flood records in Mazandaran province, this region is regarded as one of the flood-prone regions of the country, and due to the floods, it has suffered many casualties and financial losses. Therefore, this study aimed to investigate the settlements at risk of flooding as one of the main goals of this research. Methods: This descriptive-analytical study was conducted based on extensive and exploratory research approaches. The required data were collected from monthly discharge and the maximum instantaneous discharge in the stations of Mazandaran province along with the population statistics of the provincial cities, as well as the statistics of the Natural Resources and Watershed Management Organization concerning the floods. Accordingly, the statistics of hydrometric stations from 1971 to 2021 of Iran's water resources management main company, the population statistics of the province based on the census of 2015, and the statistics of floods that occurred from the beginning to 2021 have been used in this study. Flood return periods were obtained in the study stations in different statistical distributions using Hyfa software. Finally, Arc GIS software (version 10.3) was used to zone floods in Mazandaran province. Findings: Based on the results, about 1013 square kilometers of the province's surface accounting for 4.25% of its total area is located in the boundaries of large floods that have a return period of 50 to 100 years. Moreover, due to the high altitude, rainy-snowy events, and the significant amount of precipitation in Sarab (Dali Chai and Lar basins) and Payab, Haraz basin has a significant runoff rate discharge so that about 500 to 600 liters of water flow from this basin annually per square meter. Conclusion: According to the obtained results, strategies have been proposed to increase resilience against flood risk using different methods.