In video streaming over vehicular communication, optimal selection of a video packet forwarder is a daunting issue due to the dynamic nature of Vehicular Ad-hoc NETworks (VANETs)and the high data rates of video. In most of the existing studies, extensive considerations of the essential metrics have not been considered. In order to achieve quality video streaming in vehicular network, important metrics for link connectivity and bandwidth efficiency need to be employed to minimize video packet error and losses. In order to address the aforementioned issues, a Road-based Multi-metric Forwarder Evaluation scheme for Multipath Video Streaming (RMF-MVS) has been proposed. The RMF-MVS scheme is adapted to be a Dynamic Self-Weighting score (DSW) (RMF-MVS+DSW) for forwarder vehicle selection. The scheme is based on multipath transmission. The performance of the scheme is evaluated using Peak Signal to Noise Ratio (PSNR), Structural SIMilarity index (SSIM), Packet Loss Ratio (PLR) and End-to-End Delay (E2ED) metrics. The proposed scheme is compared against two baseline schemes including Multipath Solution with Link and Node Disjoint (MSLND) and Multimedia Multi-metric Map-aware Routing Protocol (3MRP) with DSW (3MRP+DSW). The comparative performance assessment results justify the benefit of the proposed scheme based on various video streaming related metrics.
20 November 2022 in International Journal of Innovative Computing
EyeKids is a tracking and monitoring system that implements Global Positioning System (GPS) technology for obtaining location data, a General Packet Radio Service (GPRS) network for data transmission, and a cloud database for storing tracking data with the main purpose of allowing a parent to ensure their child safety remotely. Child safety is the number one priority of any parent. They are concerned about their child’s well-being and wanted to keep an eye on their child’s every movement. This project is meant to provide a solution to the concerned parents. This system includes three main components, a child tracking device, a parent-side application, and a cloud database. The tracking device is built using Arduino Uno Microcontroller Board, SIM808 GPS/GPRS/GSM module, and a push button. The tracking device sends its device ID, latitude, and longitude to the PHP server first using an HTTP request before it goes through the uploading process on the server to Firebase Database via HTTPS. Mobile EyeKids Parent-side application is based on Android where it is developed using the Flutter framework and implements Firebase Authentication for user authentication. The application consists of three main tracking functions, tracker, path tracking, and tracking analysis. The tracker function allows parents to track their child’s location based on the coordinate obtained which is displayed on a map. Path tracking functions show paths taken by children throughout a selected day on the map. Parents also are able to view analysis of child movement based on tracking data stored in the cloud database. The integration of hardware and software components of the system is evaluated to assess the correctness of the system through white box testing, black box testing, and user acceptance testing. The project follows a Rational Unified Process development model that has been adjusted to suit the size of the project and its requirements. The project has successfully developed and tested to be able to track child movement when the device is turned on and provide child location reports on a monthly basis.
10 November 2023 in Applied Mathematics and Computational Intelligence (AMCI)
LSTM is a promising tool for predicting the stock exchange. Still, when the LSTM Model faces an anomaly problem with a dataset of Bitcoin that has hit more change in value by fluctuation, it can be a problem for producing good evaluation results such as RMSE. This research is an improvement over the discoveries of previous research. We tried another perspective besides using five years of historical data prices to predict a six-day value. We found that the results of RMSE were not very good but exhibited good results on MAPE as a comparison evaluation method. We are using the last six days to predict the next day. Logically, this dataset has good dataset stability, but the dataset has quite a significant minute-by-minute change in day-by-day value. Furthermore, CNN-LSTM was selected in this research to give another perspective and improve the results. The results were quite good and greatly improved previous research.
21 May 2018 in International Journal of Innovative Computing
Data Mining is a computational process that able to identify patterns, trends and behaviour from large datasets. With this advantages, data mining has been applied in many fields such as finance, healthcare, retail and so on. However, information disclosure become one of an issue during data mining process. Therefore, privacy protection is needed during data mining process which known as Privacy Preserving Data Mining (PPDM). There are several techniques available in PPDM and each of the techniques has its’ own benefits and drawbacks. In this research, perturbation technique is selected as privacy preserving technique. Perturbation technique is a method that alters the original data value before the application of data mining. In PPDM applications, perturbation technique able to provide a protection of data privacy but the accuracy of data should not be ignored too. In this research, three perturbation techniques are selected which are additive noise, data swapping and resample. For data mining techniques, two methods of classification are selected which are Naïve Bayes and Support Vector Machines (SVM). With the selection of these techniques, the experimental results are evaluated based on the hiding failure, accuracy and precision. For overall result, resample is selected as the best perturbation technique in naïve bayes and SVM classification for both glass and ionosphere datasets.
4 March 2026 in Journal of Information Systems Engineering and Business Intelligence
Background: The eradication of Polio virus is one of the important public health issues. In order to remove this virus, some well-planned methods are required. Objective: The aim of this paper is to assess GIS usage in different aspects of surveillance of polio virus. Specifically, the focus of this research is GIS applications, their practical challenges, and limitations in the context of polio viruses. Methods: Based on the systematic review of 36 peer reviewed studies across several academic research databases, we evaluated how GIS is used in polio control and eradication. Results: The findings include applications of GIS in several aspects. Few of these include vaccination coverage, analysis of disease patterns, and integration with existing healthcare information networks. Moreover, several important obstacles were also identified in context of shortcomings of data, infrastructure and expertise. Conclusion: The findings of this study offer useful guidance for healthcare workers and policymakers involved in eradication of polio viruses. Keywords: Challenges, Geographic Information Systems (GIS), Polio virus, Surveillance, Systematic Review
31 December 2024 in Journal of Engineering and Technology (JET)
This research explores the development of a hybrid consensus algorithm that combines the benefits of Proof of Authority (PoA), Delegated Proof of Stake (DPoS), and threshold cryptography to create a secure, efficient, and scalable consensus mechanism for resource-constrained devices. The proposed algorithm addresses traditional consensus algorithms' limitations in resource-constrained environments, where energy efficiency, security, and decentralisation are crucial. By leveraging the strengths of PoA, DPoS, and threshold cryptography, this hybrid approach is anticipated to provide a robust and adaptable consensus mechanism to support many applications in IoT, edge computing, and other resource-constrained domains. The research aims to investigate the feasibility, performance, and security of this hybrid consensus algorithm and its potential to enable secure, decentralised, and scalable blockchain-based systems for resource-constrained devices.