Asian Journal of Research in Computer Science

The ability to process, understand and interact in natural language carries high importance for building a Intelligent system, as it will greatly affect the way of communicating with the system. Deep Neural Networks (DNNs) have achieved excellent performance for many of machine learning problems and are widely accepted for applications in the field of computer vision and supervised  learning. Although DNNs work well with availability of large labeled training set, it cannot be used to map complex structures like sentences end-to-end. Existing approaches for conversational modeling are domain specific and require handcrafted rules. This paper proposes a simple approach based on use of neural networks’ recently proposed sequence to sequence framework. The proposed model generates reply by predicting sentence using chained probability for given sentence(s) in conversation. This model is trained end-to-end on large data set. Proposed approach uses Attention to focus text generation on intent of conversation as well as beam search to generate optimum output with some diversity.Primary findings show that model shows common sense reasoning on movie transcript data set.

In this paper, a prototype is proposed of integrating various features and functionalities of different open source GIS software to improve decision-making in small and medium companies. The paper shows possibilities of integrating various open source GIS software to support decision making. Open source software features is combined with the functionalities of GIS such as processing using Quantum GIS, storing and analyzing of spatial data to produce results using PostgreSQL, Providing and sharing Geo-data over the network locally or over the globe using Geoserver, The prototype is based on the three basics features low /free cost of using GIS open source software, simplicity and usability, multiplatform supporting. The integration of open source software is appropriate and successful for the use of companies in the field of GIS, this initiative represents a suitable business solutions that do not consume a lot of money and training to develop the skills of the technicians in this field, therefore, this will open the door for other companies to follow this trend. This prototype provides an opportunity for open source software components to process and store data in databases or shares the results over different networks.

In this paper, the author presents an abstract model of a computable machine that is passive to inputs. The model is conceptually a deaf machine that is basically an automaton that does not have any acceptance state. The Deaf machine may have one or more normal states and can even have infinite states (uncountable normal states). The Machine can not recognize any language either formal informal. The Proposed model is a finite state machine without the accept state and cannot recognize any language.

Today an E-mail service is one principal tool in our daily work and life. We cannot dispense Email services. Spammers continue to develop their techniques to flood our inbox daily. On the other hand, websites are created to be in different types of different goals like news, sports, environments, staticialists, governments, etc. Websites may be in its environments, static sites, programs, or databases, and very often a combination of the three integrating relational databases as a back-end. Websites require intensive care in configuration and programming to assure a security factor, confidentiality, and trustworthiness of the published information. Most websites have many scripts that give visitors elastic options to share some subject's links URL with their friends one of that by using a tell a friend form. One of most well-known attacks over the internet is done by SQL-injection, though SQL-injections back to exploits, weak validation of textual input that is used to build tell friend scripts which cause dangerous attacks threat email user's privacy through cheating attacks. In this paper, the author aims to analyse a tell friend exploit and proposes a solution to stop this exploit.

Category: Information Security.

Quality of service has become the major challenges being faced by telecommunication services users. Service providers (MTN, GLO and AIRTEL) have tried as much as possible to fight the disease that is faced by this sector by minimizing the losses that occurs during transmission from the transmitter to the end users, but signal losses still remain the major challenges in this generation and the generation to come. This is so because losses cannot be eliminated in communication systems and as such noise cannot be eliminated, losses has direct impact on the quality of service. This papers focuses on the signal strength in the selected locations using an application called network monitor to measure the signal strength in the selected locations, how the environments affect the quality of service and thereby drawing a conclusion on the best service provider to use by the occupants of these locations.