Wyniki wyszukiwania - BazTech

1

Novel approach for big data classification based on hybrid parallel dimensionality reduction using spark cluster

Ali Ahmed Hussein, Abdullah Mahmood Zaki

Computer Science

|

2019

|

Vol. 20 (4)

411--429

EN

The big data concept has elicited studies on how to accurately and efficiently extract valuable information from such huge dataset. The major problem during big data mining is data dimensionality due to a large number of dimensions in such datasets. This major consequence of high data dimensionality is that it affects the accuracy of machine learning (ML) classifiers; it also results in time wastage due to the presence of several redundant features in the dataset. This problem can be possibly solved using a fast feature reduction method. Hence, this study presents a fast HP-PL which is a new hybrid parallel feature reduction framework that utilizes spark to facilitate feature reduction on shared/distributed-memory clusters. The evaluation of the proposed HP-PL on KDD99 dataset showed the algorithm to be significantly faster than the conventional feature reduction techniques. The proposed technique required >1 minute to select 4 dataset features from over 79 features and 3,000,000 samples on a 3-node cluster (total of 21 cores). For the comparative algorithm, more than 2 hours was required to achieve the same feat. In the proposed system, Hadoop’s distributed file system (HDFS) was used to achieve distributed storage while Apache Spark was used as the computing engine. The model development was based on a parallel model with full consideration of the high performance and throughput of distributed computing. Conclusively, the proposed HP-PL method can achieve good accuracy with less memory and time compared to the conventional methods of feature reduction. This tool can be publicly accessed at https://github.com/ahmed/Fast-HP-PL.

2

An algorithm for vehicle identification by on-board Bluetooth devices exploiting Big-Data tools

Bazan M., Janiczek T., Kurda R., Matusiak K., Sak Ł.

Zeszyty Naukowe Wyższej Szkoły Technicznej w Katowicach

|

2017

|

nr 9

7--21

EN

Nowadays, vehicles are equipped with various on-board devices that work in Bluetooth technology and log on to the ITS infrastructure whenever passing by Bluetooth readers. The location of Bluetooth readers is an important issue for travel time prediction in urban areas. Bluetooth technology is used to enhance travel time prediction accuracy and is additional to vehicle license number identification. The algorithms for travel time prediction are used by such technologies e.g., TRAX to offer the road user an alternative route to traverse the most congested regions of the city in the most efficient way. In this paper we present the implementation of the algorithm that enables us to match Bluetooth on-board devices, and also cell phones that are mounted or are just in vehicles of road users. Since the ITS is a source of an enormous and increasing amount of data for this purpose we engage Big Data tools such as Apache HaDoop and Apache Spark. To build Map-Reduce tasks we use Hive-SQL. The algorithm is tested on ITS data from the city of Wroclaw. The results of the algorithm may be used to locate stolen vehicles.

PL

Współczesne pojazdy wyposażane są w wiele różnych urządzeń Bluetooth, które logują się do infrastruktury ITS za każdym razem gdy przejeżdżają one w zasięgu czytników Bluetooth. Położenie czytników Bluetooth jest zagadnieniem istotnym dla metod predykcji czasu przejazdu w regionach zurbanizowanych. Technologia Bluetooth jest użyta do poprawy dokładności czasu przejazdu i jest uzupełnieniem dla identyfikacji pojazdów po numerach rejestracyjnych. Algorytmy do predykcji czasu przejazdu są używane do proponowania użytkownikom trasy alternatywnej w celu przejazdu przez najbardziej zatłoczone regiony miasta w sposób najbardziej efektywny. W artykule jest prezentowana implementacja algorytmu, który pozwala połączyć urządzenia Bluetooth i telefony znajdujące się w pojazdach z samymi pojazdami. Do tego celu angażuje się narzędzia Big Data takie jak Apache HaDoop i Apache Spark. Do zbudowania zadań Map-Reduce używa się Hive-SQLa. Algorytm był testowany na danych z wrocławskiego ITS. Wyniki działania algorytmu mogą być użyte do lokalizowania skradzionych pojazdów.

3

Analysis of pressure ratio in the intake in dependence on high-voltage behaviours

Šebök M., Gutten M., Korenčiak D., Bartłomiejczyk B.

Przegląd Elektrotechniczny

|

2013

|

R. 89, nr 2a

126--129

EN

Power control in spark ignition engines by regulating the intake air is performed. The control unit needs information about the air pressure conditions which then enters the combustion chamber. The information about the intake air pressure is an important quantity for optimal control of combustion mixtures. The paper describes some types of sensors that are used to measure the air intake temperature. Air pressure in the intake manifold affects the operation of the engine and also the extent of the loss or utility of the engine operation. Size of the over voltage sparks is also influenced by the air pressure in the combustion chamber which is proportional to the pressure manifold.

PL

W artykule przedstawiono wyniki badań dotyczących sterowania energią w silnikach o zapłonie iskrowym, poprzez regulację dostarczanego powietrza. Opracowany algorytm korzysta z informacji o ciśnieniu powietrza w komorze spalania. Omówiono także niektóre rodzaje czujników pomiaru temperatury pobranego powietrza.