Zainab Ali Mohammed; Mohammed Najm Abdullah2; Imad Husain Al Hussaini
Volume 21, Issue 1 , March 2021, , Page 1-15
Abstract
Traffic incidents dont only cause various levels of traffic congestion but often contribute to traffic accidents and secondary accidents, resulting in substantial loss of life, economy, and productivity loss in terms of injuries and deaths, increased travel times and delays, and excessive consumption ...
Read More ...
Traffic incidents dont only cause various levels of traffic congestion but often contribute to traffic accidents and secondary accidents, resulting in substantial loss of life, economy, and productivity loss in terms of injuries and deaths, increased travel times and delays, and excessive consumption of energy and air pollution. Therefore, it is essential to accurately estimate the duration of the incident to mitigate these effects. Traffic management center incident logs and traffic sensors data from Eastbound Interstate 70 (I-70) in Missouri, United States collected during the period from January 2015 to January 2017, with a total of 352 incident records were used to develop incident duration estimation models. This paper investigated different machine learning (ML) methods for traffic incidents duration prediction. The attempted ML techniques include Support Vector Machine (SVM), Random Forest (RF), and Neural Network Multi-Layer Perceptron (MLP). Root mean squared error (RMSE) and Mean absolute error (MAE) were used to evaluate the performance of these models. The results showed that the performance of the models was comparable with SVM models slightly outperforms the RF, and MLP models in terms of MAE index, where MAE was 14.23 min for the best-performing SVM models. Whereas, in terms of the RMSE index, RF models slightly outperformed the other two models given RMSE of 18.91 min for the best-performing RF model.
Hayder Waleed Shnain1; Mohammed Najm Abdullah2; Hassan Awheed Jeiad3
Volume 21, Issue 1 , March 2021, , Page 62-72
Abstract
Recently, video files and images have became the dominant media material for transmitting or storing across different applications that are used by different people. So, there was a serious need to find more effective and efficient video compression techniques to reduce the large size of such multimedia ...
Read More ...
Recently, video files and images have became the dominant media material for transmitting or storing across different applications that are used by different people. So, there was a serious need to find more effective and efficient video compression techniques to reduce the large size of such multimedia files. This paper proposes SIMD based FPGA lossless JPEG video compression system with the facility of scalability. Generally, the proposed system consists of a software side and a hardware side. The digital video file is prepared to be processed by the hardware side frame by frame on the software side. The hardware side is proposed to consist of two main processing circuits, which are the prediction circuit for calculating the predicted value of each pixel in the certain frame and the encoding circuit that was represented by a modified RLE (Run-Length-Encoder) to encode the result obtained through subtracting the predicted value from the real value for each pixel to produce the final compressed video file. The compression ratio obtained for the proposed system is equal to 1.7493. The throughput improvement for the two and four processing units basing on SIMD architecture was 100 MP/s and 200 MP/s, respectively. The clock results showed that the number of clocks required had become 50% and 25% when using two processing units and four processing units, respectively, from the number of clocks using single processing units.
Mohammed Najm Abdullah; Mohanad J. Ahmed
Abstract
The number of office transactions continually increasing ,therefore,several techniques proposed to improve quality of service for the office work.Improvements including electronic archiving limited; they didn’t solve theproblem of transferring parcels. Thus, paper transactions still exist inside ...
Read More ...
The number of office transactions continually increasing ,therefore,several techniques proposed to improve quality of service for the office work.Improvements including electronic archiving limited; they didn’t solve theproblem of transferring parcels. Thus, paper transactions still exist inside asingle office building and the transfer needed within a time limit. This leads tosuggesting the autonomous vehicle for solving the delivery problem. In-order-toenable such the navigation within the indoor environment, an acceptablelocalization accuracy must exist. The wireless fingerprinting with GeneralizedRegression Neural Network (GRNN) for classification suggested in thisresearch for localization estimation. Furthermore, the estimated location fusedwith the Odometer to bring more stable results. The Accuracy gained about4.1cm which enables the vehicle to localize and navigate. ZigBee modules withArduino microcontrollers are the basic items of the research.
Afrah Salman Dawood; Mohammed Najm Abdullah
Abstract
Being able to send different types of data (i.e. text, audio, or video) through thenetwork is the most important aspect of networks. Different networks have different issuesand restrictions while sending data. These restrictions are basically the QoS (Quality ofService) metrics and security. The recent ...
Read More ...
Being able to send different types of data (i.e. text, audio, or video) through thenetwork is the most important aspect of networks. Different networks have different issuesand restrictions while sending data. These restrictions are basically the QoS (Quality ofService) metrics and security. The recent Software-Defined Networking (SDN) that aimsto separate the control plane from the data plane can be applied where Businessrequirements are not responsible for the way the network is configured; instead, it is theresponsibility of the high-level business policies and objectives. SDN gives preferabletechniques for centralized dynamic management and control configurations. In this work,a proposed model has been estimated and discussed to promote QoS requirements in somesuggested topologies. Adaptive Resource Management (ARM) and control to send differenttypes of data through different hosts have been investigated. The intended requirementsare basically the capacity and delay of traffic metrics sent through different hosts throughthe network. It produces a mathematical model and implementation for three proposedalgorithms to enhance the quality of a sample video sent from source host to destinationhost by Visible Light Communication (VLC)-media player in three different topologies.These algorithms (statistical, MOGA, and PSO) have been implemented using Mininetemulator, FNSS tool, PULP, and network libraries; with two types of controllers whichare Floodlight and OVS under Linux operating system and in python programminglanguage.