Open Access Original Research Article

Integrated Distribution Network Design through Simulation

Adriana Martínez- Osorio, Santiago-Omar Caballero- Morales, Diana Sánchez- Partida, Patricia Cano- Olivos

Asian Journal of Research in Computer Science, Page 1-15
DOI: 10.9734/ajrcos/2020/v6i230153

Simulation is important to validate quick-response scenarios, providing an extent on how technology can effectively upgrade a process. Thus, computer simulation is a crucial aspect for supply chain management. The present paper analyses a distribution problem which involves inventory supply planning. Then, a simulation model was developed to evaluate its current performance and to provide a better operation scheme. The advances of this work extend on the modelling and simulation of distribution networks that must comply with retailers’ demands at end points.

Open Access Original Research Article

Sign Language Digit Recognition Using Different Convolutional Neural Network Model

Md. Bipul Hossain, Apurba Adhikary, Sultana Jahan Soheli

Asian Journal of Research in Computer Science, Page 16-24
DOI: 10.9734/ajrcos/2020/v6i230154

An enormous number of world populations in current time are unique in that sense that they have no broad language because of the absence of their hearing capability. The people with hearing impairment have their own language called Sign Language however it is hard for understanding to general individuals [1]. Sign digits are additionally a significant piece of gesture based communication. So a machine interpreter is important to permit them to speak with general individuals. For making their language justifiable to general individual’s computer vision based arrangements are notable these days. In this exploration of work we target to develop a model based on CNN to deal with the recognition of Sign Language digits. A dataset of 10 classes is used to train (70%), validation (20%) and test (10%) of the network. We consider three different models of CNN network to train and test the accuracy of sign digit. Among the three model transfer learning based pre-trained CNN performs better with test accuracy of 92%.

Open Access Original Research Article

Automated Duck Egg Classifier with Web-Based Monitoring System

Jomelyn L. Ongrea, Nikka E. Allawan, Noel P. Sobejana

Asian Journal of Research in Computer Science, Page 25-35
DOI: 10.9734/ajrcos/2020/v6i230155

The main objectives of the research were to develop a module that classify fertilized/unfertilized duck eggs according to its classification using Light Dependent Resistor during candling process of the duck eggs, a project that segregate the duck eggs to its designated classification area using servo motor, to develop a webpage that displays the number of classified duck eggs in a tabular and graphical presentation using Windows Form and to capture the level of effectiveness of the Automated Duck Egg Classifier with Web-Based Monitoring System in terms of functionality, reliability, usability, efficiency, maintainability and portability. Recipient-beneficiary of the project is the balut producer's industry. The method that was used by the project-developers was waterfall approach as a process model for the system. The project-developers used Visual Studio 2012 as front-end and Text File as back end of the system. Asp.Net will be used for designing the user's interface. Using these applications, the project team created a Web-Based Application that displays the number of classified duck eggs which could be presented in a tabular and graphed. Therefore, the study intended to help the balut producer’s industry. Project developers developed an Automated Duck Egg Classifier with Web-Based Monitoring System that able to solve the aforesaid problems of the producers. The common problem encountered by the said industry is the manual process in classifying duck eggs. After the project was tested, the developers concluded that the project finally resolved the traditional problems of classifying duck eggs as the balut expert stated.

Open Access Original Research Article

Accuracy Implementation of Medical Record Management Information System with Waterfall Design System and ISO 9126

Wahyu Wijaya Widiyanto, Sri Wulandari

Asian Journal of Research in Computer Science, Page 36-45
DOI: 10.9734/ajrcos/2020/v6i230156

Aims: Based on the observations of researchers, some health facilities still use manual processes / have not been documented by the information system resulting in slow service, this study aims to improve health services with a medical record information system.

Methodology: The method used in this study is an analysis of information systems with the waterfall method and accuracy testing with ISO 9126.

Results: The results of this medical record management information system run well based on black-box testing and white box results obtained both from an average value of 82 based on the ISO 9126 scale conversion table.

Conclusion: Based on the results of the average value obtained from the validation test carried out on 3 expert examiners, it can be concluded that the application for the validation system for the validation and distribution of this letter has met the ISO 9126 standard with an average good interpretation of a total value of 82, and according to be able to simplify the process of Patient Medical Record Data Management without neglecting the safety aspects of the validation and distribution process, minimizing data loss, simplifying the reporting process and facilitating the processing of patient medical record data.

Open Access Original Research Article

Identifying and Isolating Zombie Attack in Cloud Computing

Peter Awon-natemi Agbedemnab, Salifu Abdul-Mumin, Zakaria Abdulrahim

Asian Journal of Research in Computer Science, Page 46-56
DOI: 10.9734/ajrcos/2020/v6i230157

The cloud computing architecture is a berth in which third party, virtual machine and cloud service providers are involved in data uploading and downloading. A major challenge in this architecture, however, is the security of the data as there exist various forms of attacks from malicious people
and devices. Among these security attacks, the zombie attack is the most advance type of attack. The zombie attack reduces network performance in terms of delay and bandwidth consumption. With zombie attack, some malicious users may join the network which, in turn takes off the data of legitimate users and at the same time enable zombie nodes to communicate with a virtual machine on behalf of the legitimate user. In this paper, a technique based on strong authentication which, is able to detect malicious users from a network and isolates them from the cloud architecture is proposed.