Accepted Papers

  • Pong game optimization using Policy Gradient Algorithm
    Aditya Singh and Vishal Gupta, BML munjal University, India

    Pong game was the titanic of the gaming industry in 20th century. Pong is the perfect example of deep reinforcement learning of ATARI game [1]. The game is extremely beneficial to improve concentration and memory capacity. Since the game is played by around 350 million people worldwide at present scenario, hence we saw the opportunity in this interesting game.]The project has a great scope in atari game development. We proposed a stochastic reinforcement learning technique of Policy Gradient algorithm to optimize Pong game . The purpose of this study is to improve the algorithms that control the game structure, mechanism and real-time dynamics. We implemented policy gradient algorithm to improve the performance and training which is significantly better than traditional genetic algorithm.

  • Software Quality Improvement Through Statistical Analysis On Process Metrics
    Karuna Prasad ,Divya MG, Sarat Chandrababu, Mangala N, C-DAC, Bangalore,India

    Software Quality can be considered as totality of features and characteristics of a product or service that bears its ability to satisfy stated or implied needs. The Quality of any software can be achieved by following by well-defined software process. These software process results into various metrics like Project metrics, Process metrics and Product metrics. Process metrics are very useful from management point of view. Process metrics can be used for improving the software development and maintenance process for defect removal and also for reducing the response time. This paper describes on importance of capturing the Process metrics during the quality audit process and also attempts to categorize them based on the nature. To reduce such defect, corrective actions are recommended.

  • Qincloud: An Agent Based System For Quering Encrypted Data In Cloud Databases
    MASHAEL M. ALSULAMI,King AbdulAziz University, Saudi Arabia

    With the rapid growth of technologies, cloud computing become more and more popular. Many organizations have been attracted by the variety of services that have been offered by the clouds in form of resources and applications. Database system is one of the most widely used systems in industry. Cloud providers offer database-as-a-service to attract more clients to use their services. However, executing queries against a cloud database is a challenging process since data are stored in encrypted form for security purposes. Cloud DB server is responsible of performing the user”Ēs query on the encrypted database without any knowledge about the meaning of the requested data to ensure the data confidentiality. Most of the existing methods focus on data confidentially and do not guarantee the performance of their techniques. In this paper, an agent based system called QinCloud for executing query efficiently over encrypted data in cloud databases is introduced. The proposed system allows users to execute queries on a cloud database server without having any intermediate proxy as a trusted server. Nevertheless, the proposed system is designed to support wide range of queries that are performed completely on the cloud DB server side. The proposed system overcomes many issues in existing systems.

  • Disaster Recovery in The Internet of Things Environment
    Omar H Alhazmi,Taibah University, Medina, Saudi Arabia

    More businesses and organizations are becoming intolerant for any down time or loss of data. Unfortunately, Disaster is always a possibility and when it occurs, focus turns to disaster recovery. Hence, effective disaster recovery plan is essential. In traditional computing environments, many disaster recovery alternatives are available; for example, remotely located alternative data centre or cloud-based disaster recovery solutions. However, for distributed heterogenous environment and platform such as Internet of things platforms traditional disaster recovery solution might be insufficient. Here, we investigate distributed disaster recovery to accommodate IoT environment. Here, we consider five- layered-architecture. In this work, we broadly discuss disaster recovery designed for Layered IoT architecture.