TVD-MRDL: traffic violation detection system using MapReduce-based deep learning for large-scale data

Maintaining a fluid and safe traffic is a major challenge for human societies because of its social and economic impacts. Various technologies have considerably paved the way for the elimination of traffic problems and have been able to effectively detect drivers’ violations. However, the high volume of the real-time data collected from surveillance cameras and traffic sensors along with the data obtained from individuals have made the use of traditional methods ineffective. Therefore, using Hadoop for processing large-scale structured and unstructured data as well as multimedia data can be of great help. In this paper, the TVD-MRDL system based on the MapReduce techniques and deep learning was employed to discover effective solutions. The Distributed Deep Learning System was implemented to analyze traffic big data and to detect driver violations in Hadoop. The results indicated that more accurate monitoring automatically creates the power of deterrence and behavior change in drivers and it prevents drivers from committing unusual behaviors in society. So, if the offending driver is identified quickly after committing the violation and is punished with the appropriate punishment and dealt with decisively and without negligence, we will surely see a decrease in violations at the community level. Also, the efficiency of the TVD-MRDL performance increased by more than 75% as the number of data nodes increased.

     

A Model for Identifying the Behavior of Alzheimer’s Disease Patients in Smart Homes

Wireless Personal Communications - In recent years, Smart Cities and Smart Homes have been studied as an important field of research. The design and construction of smart homes have flourished so...     

Study of relation between the gamma flux buildup factors and source geometry by M-C simulation

This paper is to achieve a gamma-ray source with the lowest rate of buildup factor, which is of great importance in medical, industrial and agricultural sciences.The flux buildup factor of gamma rays is calculated by the MCNP code for point, linear, surface and volume sources with shield layers of lead, iron and aluminum. The results show that for the high Z shielding material, the flux buildup factor of coaxial cylindrical sources is the lowest(1.6–2.3)of all sources, while for low Z shielding materials, the coaxial disk surface sources have smaller buildup factor(1.45–1.6).     

Removal of arsenic from aqueous solutions by an adsorption process with titania–silica binary oxide nanoparticle loaded polyacrylonitrile polymer

A new and simple method was developed to produce gelatin nanoparticles of ～ 30–40 nm for use as carriers for drug release applications. The nanoparticles were uniform in size and well dispersed. An anticancer drug, 5‐fluorouracil, was encapsulated with an efficiency as high as 85%. The nanoparticles showed sustained release of 5‐fluorouracil, and release rates varied with amount of crosslinking in the nanoparticles. © 2011 Wiley Periodicals, Inc. J Appl Polym Sci, 2011.     

Heat Transfer Coefficient for a Packed Bed of Shredded Materials at Low Peclet Numbers

The application of the Nusselt number (Nu) correlation of a packed bed of spherical particles overestimates the rate of heat transfer in the packed beds of shredded materials. This is due to the dependence of flow distribution on the particle geometry. This discrepancy is even more pronounced due to a channeling effect at low Peclet numbers (Pe). In this study, the heat transfer coefficient for a packed bed of shredded materials was derived at low Peclet numbers. In deriving the correlation, both numerical simulation and experimental work were employed. The experimental work was carried out in a packed bed of combustible materials for the flow rates of 15 × 10^{? 6} to 50 × 10^{? 6} m ³/s and a temperature range of 30 to 60°C. Using the results of experimental work along with numerical modeling and applying a power law formulation, the best-fit Nusselt number for the packed bed of shredded materials for Pe < 25 was derived to be Nu = 0.015 0.11 + Pe ^0.73 . The Nusselt number calculated from this correlation is in good agreement with the experimental data.     

Cooperative Subcarrier Allocation and Power Allocation in the Downlink of an Amplify-and-Forward OFDM Relaying System

The increasing use of relays in wireless communication systems is a driving force to explore innovative techniques that can improve the quality of service as well as enhance the coverage in wireless systems. In this article, we propose a two-step approach for subcarrier allocation and power allocation in the downlink of an OFDM-based amplify-and forward relaying system. In the first step, the total power is allocated to mobile users and relays based on the optimum power ratio derived for the single-relay system. In the second step, subcarriers are assigned to the users based on cooperative subcarrier allocation algorithms. Compared to the non-cooperative algorithm with flat power allocation, the total throughput is shown to improve by applying the two-step cooperative subcarrier allocation and power allocation algorithms.