Software Performance Evaluation Research Articles

Performance evaluation of software defined networking into vanets system

Performance evaluation of software defined networking into vanets system

Head and neck automatic multi-organ segmentation on Dual-Energy Computed Tomography

Background and purposeDeep-learning-based automatic segmentation is widely used in radiation oncology to delineate organs-at-risk. Dual-energy CT (DECT) allows the reconstruction of enhanced contrast images that could help with manual and auto-delineation. This paper presents a performance evaluation of a commercial auto-segmentation software on image series generated by a DECT. Material and methodsDifferent types of DECT images from seventy four head-and-neck (HN) patients were retrieved, including polyenergetic images at different voltages [80 kV reconstructed with a kernel corresponding to the commercial algorithm DirectDensity™ (PEI80-DD), 80 kV (PEI80), 120 kV-mixed (PEI120)] and a virtual-monoenergetic image at 40 keV (VMI40). Delineations used for treatment planning were considered as ground truth (GT) and were compared with the auto-segmentations performed on the 4 DECT images. A blinded qualitative evaluation of 3 structures (thyroid, left parotid, left nodes level II) was carried out. Performance metrics were calculated for thirteen HN structures to evaluate the auto-contours including dice similarity coefficient (DSC), 95th percentile Hausdorff distance (95HD) and mean surface distance (MSD). ResultsWe observed a high rate of low scores for PEI80-DD and VMI40 auto-segmentations on the thyroid and for GT and VMI40 contours on the nodes level II. All images received excellent scores for the parotid glands. The metrics comparison between GT and auto-segmented contours revealed that PEI80-DD had the highest DSC scores, significantly outperforming other reconstructed images for all organs (p < 0.05). ConclusionsThe results indicate that the auto-contouring system cannot generalize to images derived from DECT acquisition. It is therefore crucial to identify which organs benefit from these acquisitions to adapt the training datasets accordingly.

Teaching Software Performance Evaluation to Undergrads: Lessons Learned and Challenges

Teaching Software Performance Evaluation to Undergrads: Lessons Learned and Challenges

Performance evaluation of smartphone-based vibration meter application software

Modern smartphones have been equipped with MEMS sensors allowing them to be used for advanced purposes. A MEMS accelerometer is embedded in the smartphone to sense motion and vibration. Recently, many smartphone-based vibration-meter applications software employed the embedded accelerometer and used them for vibration monitoring and field measurement. However, the accuracy of this kind of vibration meter has not known yet. In this paper, we discuss about the evaluation of smartphone-based vibration meter using the standard method for vibration meter calibration described in the ISO 16063-21. A vibration measurement by the smartphone-based vibration meter is compared to the reading of the reference accelerometer type B&K 8305. The evaluation was conducted in a frequency range of 10 Hz to 50 Hz with the amplitude of 0.1 G to 1 G. This study showed that the accuracy of the smartphone-based vibration meter is decreased in the higher frequency range.

Holistic System Design Evaluation Through Expanded MATE

According to Buede and Miller, not applying a holistic simulation and modeling approach to early design evaluation practices and trade studies results in greater developmental costs, time to market, and unforeseeable system-level design consequences. Completed research is presented for an innovative methodology that enhances the capacity of conventional design evaluations by integrating new types of simulations consistently into the existing Multi-attribute Tradespace Exploration (MATE) design evaluation architecture. This enhancement is particularly important for any envisioned software-intensive system that introduces greater system complexity. According to Ross et al., MATE was originally developed to guide engineering design and initial product selection by exploring candidate designs to deliver utility-based solutions. Unfortunately, the MATE methodology does not support software design evaluation and integration into complex systems. The results presented validate MATE improvements that are scalable and extensible to any software-based system of varying complexity and application. The subject research provides proof of this concept by focusing on sensor systems as an initial practical demonstration due to their rapidly expanding commercial use and Internet of Things (IoT) applications. Project engineers and especially software developers in any product field will benefit from this design method by leveraging its holistic evaluation of software and hardware system design performance for more efficient product design identification and implementation.

Algorithm development and hardware implementation for medical image compression system: a review

&lt;span&gt;In the high-tech world, medical imaging is very important to diagnose and analyze illness inside human body. The increasing number of patients annually has continuously growth the amount of medical imaging data generated and directly causes a demand for data storage. Generally, medical images are rich with data, where these data are important for diagnosing purpose. However, some of the data represents redundant information and sometimes can be discarded. Thus, the research area on medical image compression dealing with three-dimensional (3-D) modalities need to be given more attention and exploration. The algorithm development using wavelet transform with software implementation are the famous topics explored among researchers, whilst fewer works have been done in utilizing curvelet transform in medical image compression. Along with that, very limited hardware implementation of 3-D medical image compression is discovered. In term of performance evaluation, most of the previous works conducted objective test compared with subjective test. To fill in this gap, medical image compression system will be reviewed, with the aim to identify the recent method used in medical image compression system. This paper thoroughly scrutinizes the recent advances in medical image compression mainly in terms of compression method, algorithm development with software and hardware implementations and performance evaluation. In conclusion, the overall picture of the medical image compression landscape, where most of the researchers more focused on algorithm development or software implementations without having the combination of software and hardware implementations.&lt;/span&gt;

A Hybrid Software Defined Networking-Based Load Balancing and Scheduling Mechanism for Cloud Data Centers

Cloud data centers provide various services using efficient and economic infrastructure to facilitate the work of IT providers, companies and different end users. But they may suffer from congestion due to the poor distribution of traffic load among the network links and consequently diminish the network performance. Software defined networking is a modern network technology described as a promising solution for the problem of cloud data center congestion. Software defined networking is distinguished in separating the control plane from the data plane and depends on centralized network control. The current paper introduces an optimized software defined networking-based load balancing and scheduling mechanism called the software defined networking load balance mechanism for cloud data center networks that benefits from the programmable abilities of software defined networking. For the performance evaluation of software defined networking load balance mechanism experiments, a common fat-tree topology is used as a data center network running on Mininet emulator under the ryusdn-controller. The performance results and comparisons of software defined networking load balance mechanism show an improvement in network throughput, link utilization and reduction in round trip time delay.

Performance analysis and evaluation of software defined networking distributed controllers in datacentre networks

Performance analysis and evaluation of software defined networking distributed controllers in datacentre networks

Performance analysis and evaluation of software defined networking distributed controllers in datacentre networks

Today network works under several problems. To solve these problems OpenFlowbased programmable software-defined network (SDN) was released. Datacenter network is one of the application areas that r...

Performance analysis for multimedia communication systems with a multilayer queuing network model

Software performance evaluation in multimedia communication systems is typically formulated into a multi-layered client-server queuing network (MLCSQN) problem. However, the existing analytical methods to MLCSQN model cannot provide satisfactory solution in terms of accuracy, convergence and consideration of interlocking effects. To this end, this paper proposes a heuristic solving method for MLCSQN model to boost the performance prediction of distributed multimedia software systems. The core concept of this method is referred to as the basic model, which can be further decomposed into two sub-models: client sub-model and server sub-model. The client sub-model calculates think time for server sub-model, and the server sub-model calculates waiting time for client sub-model. Using a breadth-first traversal from leaf nodes to the root node and vice versa, the basic model is then adapted to MLCSQN, with net sub-models iteratively resolved. Similarly, the interlocking problem is effectively addressed with the help of the basic model. This analytical solver enjoys advantages of fast convergence, independence on specific average value analysis (MVA) methods and eliminating interlocking effects. Numerical experimental results on accuracy and computation efficiency verify its superiority over anchors.

Trade-off of security and performance of lightweight block ciphers in Industrial Wireless Sensor Networks

Lightweight block ciphers play an indispensable role for the security in the context of pervasive computing. However, the performance of resource-constrained devices can be affected dynamically by the selection of suitable cryptalgorithms, especially for the devices in the resource-constrained devices and/or wireless networks. Thus, in this paper, we study the trade-off between security and performance of several recent top performing lightweight block ciphers for the demand of resource-constrained Industrial Wireless Sensor Networks. Then, the software performance evaluation about these ciphers has been carried out in terms of memory occupation, cycles per byte, throughput, and a relative good comprehensive metric. Moreover, the results of avalanche effect, which shows the possibility to resist possible types of different attacks, are presented subsequently. Our results show that SPECK is the software-oriented lightweight cipher which achieves the best performance in various aspects, and it enjoys a healthy security margin at the same time. Furthermore, PRESENT, which is usually used as a benchmark for newer hardware-oriented lightweight ciphers, shows that the software performance combined with avalanche effect is inadequate when it is implemented. In the real application, there is a need to better understand the resources of dedicated platforms and security requirement, as well as the emphasis and focus. Therefore, this case study can serve as a good reference for the better selection of trade-off between performance and security in constrained environments.

The performance evaluation of multi-image 3D reconstruction software with different sensors

Three dimensional modelling of the objects is one the most discussed issues in Photogrammetry and Computer Vision. One of the factors affecting the accuracy of the obtained model in image-based methods is the software and algorithm to generate the model. Another important factor is the type of imaging sensor. Due to availability of cell phone sensors to the public, popularity of professional sensors and the advent of stereo sensors, a question raised about which imaging sensor can lead to more accurate and complete model. Although many research have been accomplished to identify a suitable software and algorithm to achieve an accurate and complete model, little attention has been paid to the type of imaging sensors and its effects on the quality of the final model. This paper aims to introduce an appropriate combination of a sensor and software to provide an accurate and complete model. To do this, different available software were compared and the most popular ones in each category were chosen. In this test, four small objects with distinct geometric properties were chosen and their accurate models as reliable true data were generated. Images were then captured using Fujifilm Real 3D stereo camera, Apple iPhone 5s and Nikon D3200 professional camera and three dimensional models of the objects were obtained using each of the software. Finally, a comprehensive comparison between the results showed that the best combination of software and sensors for generating three-dimensional models is directly related to the type of imaging sensors, the software and object shape. Generally better quantitative and qualitative results were obtained by using the Nikon D3200 professional camera.

IMPLEMENTATION METHOD ON MEDICAL IMAGE COMPRESSION SYSTEM: A REVIEW

The rapid development of medical imaging and the invention of various medicines have benefited mankind and the whole community. Medical image processing is a niche area concerned with the operations and processes of generating images of the human body for clinical purposes. Potential areas such as image acquisition, image enhancement, image compression and storage, and image based visualization also include in medical image processing analysis. Unfortunately, medical image compression dealing with three-dimensional (3-D) modalities still in the pre-matured stage. Along with that, very limited researchers take a challenge to apply hardware on their implementation. Referring to the previous work reviewed, most of the compression method used lossless rather than lossy. For implementation using software, MATLAB and Verilog are the famous candidates among researchers. In term of analysis, most of the previous works conducted objective test compared with subjective test. This paper thoroughly reviews the recent advances in medical image compression mainly in terms of types of compression, software and hardware implementations and performance evaluation. Furthermore, challenges and open research issues are discussed in order to provide perspectives for future potential research. In conclusion, the overall picture of the image processing landscape, where several researchers more focused on software implementations and various combinations of software and hardware implementation.

Introduction and Use of an Education-notification Application for Patients Undergoing Heart Valve Replacement

Proper education and notification of patients undergoing heart valve replacement is of paramount importance. The past decade has witnessed a growing interest in the use of modern, advanced technologies in medicine and patient education. This study aimed to introduce an education-notification application for patients undergoing heart valve replacement. Research was carried out in two phases of software design and performance evaluation. The first phase consisted of two stages: development of educational materials and notifications befitting to the application and algorithm design. The second phase of the study involved the assessment of the viewpoints of 30 patients undergoing heart valve replacement using a researcher-made questionnaire. Validity and reliability of the questionnaire were confirmed using descriptive statistics and Mann-Whitney U test. According to the results, the designed education-notification software was described as “good” or “very good” by 81.3% (n=24) of the participants.

Performance evaluation of hardware and software for spect cardiac imaging

Myocardial perfusion SPECT is used in the non invasive assessment of coronary artery disease. This talk describes the design of new iterative reconstruction algorithms (IRR) and of heart-dedicated solid-state SPECT cameras for Myocardial Perfusion Imaging and discuss how these devices improve image quality while reducing study time and/or radiation dose to the patient. Methods The relative performances of IRR and gammacameras were studies over a wide range of acquisition count statistics, also in respect to conventional reconstruction software (OSEM and FBP), using an anthropomorphic phantom and selected physical figures of merit for image evaluation. Results and discussion IRR always determined significant improvements in all indices in comparison to FBP or OSEM. Their performances depend on the combined application of scatter and/or attenuation corrections that take full advantage of the capability of such algorithms. The impact of count statistics on the performances of IRR can be neglected down to a quarter of the reference study count statistics. As for the new solid state gammacameras D-SPECT showed a lower LV wall thickness and an inferior sharpness than D530c. No significant differences were found in terms of contrast or CNR. The regional normalized tracer uptake is maintained across all count densities up to a quarter of a standard study count statistic with conventional cameras and half with advanced systems. To compare data from the analysis of polar maps across different systems will require the adoption of specific normality databases, developed for each system coupled with the reconstruction method employed. Myocardial perfusion SPECT is used in the non invasive assessment of coronary artery disease. This talk describes the design of new iterative reconstruction algorithms (IRR) and of heart-dedicated solid-state SPECT cameras for Myocardial Perfusion Imaging and discuss how these devices improve image quality while reducing study time and/or radiation dose to the patient. The relative performances of IRR and gammacameras were studies over a wide range of acquisition count statistics, also in respect to conventional reconstruction software (OSEM and FBP), using an anthropomorphic phantom and selected physical figures of merit for image evaluation. IRR always determined significant improvements in all indices in comparison to FBP or OSEM. Their performances depend on the combined application of scatter and/or attenuation corrections that take full advantage of the capability of such algorithms. The impact of count statistics on the performances of IRR can be neglected down to a quarter of the reference study count statistics. As for the new solid state gammacameras D-SPECT showed a lower LV wall thickness and an inferior sharpness than D530c. No significant differences were found in terms of contrast or CNR. The regional normalized tracer uptake is maintained across all count densities up to a quarter of a standard study count statistic with conventional cameras and half with advanced systems. To compare data from the analysis of polar maps across different systems will require the adoption of specific normality databases, developed for each system coupled with the reconstruction method employed.

Evaluación de desempeño de software para el análisis espectral de señales de voz en una arquitectura MIPS

Evaluación de desempeño de software para el análisis espectral de señales de voz en una arquitectura MIPS

DoKnowMe

Software engineering considers performance evaluation to be one of the key portions of software quality assurance. Unfortunately, there seems to be a lack of standard methodologies for performance evaluation even in the scope of experimental computer science. Inspired by the concept of "instantiation" in object-oriented programming, we distinguish the generic performance evaluation logic from the distributed and ad-hoc relevant studies, and develop an abstract evaluation methodology (by analogy of "class") we name Domain Knowledge-driven Methodology (DoKnowMe). By replacing five predefined domain-specific knowledge artefacts, DoKnowMe could be instantiated into specific methodologies (by analogy of "object") to guide evaluators in performance evaluation of different software and even computing systems. We also propose a generic validation framework with four indicators (i.e. usefulness, feasibility, effectiveness and repeatability), and use it to validate DoKnowMe in the Cloud services evaluation domain. Given the positive and promising validation result, we plan to integrate more common evaluation strategies to improve DoKnowMe and further focus on the performance evaluation of Cloud autoscaler systems.

C.387 - Evaluation of commercial software performance in retrieving information from merged SPECT and CT images: A phantom study

C.387 - Evaluation of commercial software performance in retrieving information from merged SPECT and CT images: A phantom study

C.348 - Performance evaluation of an adaptive threshold segmentation software for PET lesion delineation

C.348 - Performance evaluation of an adaptive threshold segmentation software for PET lesion delineation

Transfer Function Modelling: A Literature Survey

Monitoring and control is very important in maintaining quality outputs, reducing downtimes and improving operation’s efficiency of processes. Transfer function modelling has been the heart of process monitoring and control. This study surveys the past, present and future of transfer function modelling. The survey found that continuous transfer function models used in modelling engineering control systems have the widest applications. Similarly, the discrete transfer function models are applied mostly in forecasting and have wide application in econometrics and the social sciences and to a little extent in the physical and life sciences. The current efforts by researchers in extending the frontiers of discrete transfer function modelling to fault diagnosis, improvement of maintenance and operation’s efficiency, determination of production process capability etc were highlighted. Finally, the future directions of research in transfer function modelling which include but not limited to: leak detection and failure prediction, improved modelling software tools, performance evaluation and improvement in chemical industries, power systems, oil and gas industries, economic and management systems etc was suggested. Our findings show that transfer function would be very important in solving manufacturing dysfunction.