The appearance of pest insects can lead to a loss in yield if farmers do not respond in a timely manner to suppress their spread. Occurrences and numbers of insects can be monitored through insect ...traps, which include their permanent touring and checking of their condition. Another more efficient way is to set up sensor devices with a camera at the traps that will photograph the traps and forward the images to the Internet, where the pest insect’s appearance will be predicted by image analysis. Weather conditions, temperature and relative humidity are the parameters that affect the appearance of some pests, such as Helicoverpa armigera. This paper presents a model of machine learning that can predict the appearance of insects during a season on a daily basis, taking into account the air temperature and relative humidity. Several machine learning algorithms for classification were applied and their accuracy for the prediction of insect occurrence was presented (up to 76.5%). Since the data used for testing were given in chronological order according to the days when the measurement was performed, the existing model was expanded to take into account the periods of three and five days. The extended method showed better accuracy of prediction and a lower percentage of false detections. In the case of a period of five days, the accuracy of the affected detections was 86.3%, while the percentage of false detections was 11%. The proposed model of machine learning can help farmers to detect the occurrence of pests and save the time and resources needed to check the fields.
The focus of this paper is to make the file system performance comparison of different versions of the same hypervisor. VirtualBox was chosen as the hypervisor, while the selected versions are ...6.0.24, 6.1.40 and the 7.0.4. The Filebench program was used for testing, which is a file system and storage benchmark application that enables the generation of a large number of workloads. It is very flexible and enables precise specification of the application's behavior. CentOS7, an operating system from the Linux family, was used as the guest operating system. As for the tests themselves, they were performed for one, two and three virtual machines running simultaneously.
This paper presents a comparison of different guest file systems on the specific hosted hypervisor. Chosen hypervisor was the VMware Workstation 15.1 and used file systems were XFS, Btrfs and ext4. ...To receive the most realistic results we decided to set identical virtual machines (VM) for all measurements: first with a single VM and latter with two VM running at the same time. The host operating system (OS) was Windows 10 and guest OS Centos 7.9. To analyze expected behavior from our hypothesis we have used Filebench measuring tool for getting test results.
The rapid technological progress has led to a growing need for more data storage space. The appearance of big data requires larger storage space, faster access and exchange of data as well as data ...security. RAID (Redundant Array of Independent Disks) technology is one of the most cost-effective ways to satisfy needs for larger storage space, data access and protection. However, the connection of multiple secondary memory devices in RAID 0 aims to improve the secondary memory system in a way to provide greater storage capacity, increase both read data speed and write data speed but it is not fault-tolerant or error-free. This paper provides an analysis of the system for storing the data on the paired arrays of magnetic disks in a RAID 0 formation, with different number of queue entries for overlapped I/O, where queue depth parameter has the value of 1 and 4. The paper presents a range of test results and analysis for RAID 0 series for defined workload characteristics. The tests were carried on in Microsoft Windows Server 2008 R2 Standard operating system, using 2, 3, 4 and 6 paired magnetic disks and controlled by Dell PERC 6/i hardware RAID controller. For the needs of obtaining the measurement results, ATTO Disk Benchmark has been used. The obtained results have been analyzed and compared to the expected behavior.
This paper presents the performance analysis of two hypervisor type-1 representatives: VMware ESXi and Microsoft Hyper-V. HD Tune Pro and ATTO benchmarks are used for the performance evaluation. Both ...hypervisors were tested in fairplay conditions with Windows Server 12 virtual machine as a guest operating system. We have set and validated the hypotheses for expected behavior based on the obtained benchmark results.
This paper addresses the performance and service comparison of two different Cloud Computing platforms: Amazon AWS and Microsoft Azure. Platforms are tested in similar virtual environments, namely ...for micro instances. Performance is measured by the collection benchmark program called Phoronix Test Suite 3, and the results are presented for Apache and Dbench benchmarks.
The topic of this paper is mathematical modeling file system performance in virtual environment with special emphasis of different CPU hardware-assisted features. Paper includes the file system ...performance comparison of three different hypervisors (virtual machine managers), on two competing processors of the same generation, using the virtualization technique. By applying full hardware virtualization, virtual machines are built on Intel and AMD processors. In this way, we can see which of CPUs have a better performance in terms of CPU hardware-assisted features, while modeling is used to interpret the results. The type-2 hypervisors are used in the work and they are Oracle VirtualBox, VMware Workstation and MS Hyper-V. All tests were performed on the filebench-1.4.9.1 tool.
This paper focuses on the performance analysis of Docker, as a leading containerization tool, on two different operating systems, Ubuntu and CentOS. The study involves mathematical modeling, ...benchmarking of Docker performance in a controlled environment on both systems. The evaluation is conducted using various performance measurement tools and metrics. The primary aim of this research is to analyze the impact of different operating systems, Ubuntu and CentOS, on the performance of Docker containers. The findings are presented through graphical representations and data analysis shedding light on the comparative performance of Docker on these two distinct platforms.