performance metrics
Recently Published Documents





Ha Huy Cuong Nguyen ◽  
Bui Thanh Khiet ◽  
Van Loi Nguyen ◽  
Thanh Thuy Nguyen

Normally web services are classified by the quality of services; however, the term quality is not absolute and defined relatively. The quality of web services is measured or derived using various parameters like reliability, scalability, flexibility, and availability. The limitation of the methods employing these parameters is that sometimes they are producing similar web services in recommendation lists. To address this research problem, the novel improved clustering-based web service recommendation method is proposed in this paper. This approach is mainly dealing with producing diversity in the results of web service recommendations. In this method, functional interest, quality of service (QoS) preference, and diversity features are combined to produce a unique recommendation list of web services to end-users. To produce the unique recommendation results, we propose a varied web service classification order that is clustering-based on web services’ functional relevance such as non-useful pertinence, recorded client intrigue importance, and potential client intrigue significance. Additionally, to further improve the performance of this approach, we designed web service graph construction, an algorithm of various widths clustering. This approach serves to enhance the exceptional quality, that is, the accuracy of web service recommendation outcomes. The performance of this method was implemented and evaluated against existing systems for precision, and f-score performance metrics, using the research datasets.

2022 ◽  
Vol 27 (2) ◽  
pp. 1-33
Zahra Ebrahimi ◽  
Dennis Klar ◽  
Mohammad Aasim Ekhtiyar ◽  
Akash Kumar

The rapid evolution of error-resilient programs intertwined with their quest for high throughput has motivated the use of Single Instruction, Multiple Data (SIMD) components in Field-Programmable Gate Arrays (FPGAs). Particularly, to exploit the error-resiliency of such applications, Cross-layer approximation paradigm has recently gained traction, the ultimate goal of which is to efficiently exploit approximation potentials across layers of abstraction. From circuit- to application-level, valuable studies have proposed various approximation techniques, albeit linked to four drawbacks: First, most of approximate multipliers and dividers operate only in SISD mode. Second, imprecise units are often substituted, merely in a single kernel of a multi-kernel application, with an end-to-end analysis in Quality of Results (QoR) and not in the gained performance. Third, state-of-the-art (SoA) strategies neglect the fact that each kernel contributes differently to the end-to-end QoR and performance metrics. Therefore, they lack in adopting a generic methodology for adjusting the approximation knobs to maximize performance gains for a user-defined quality constraint. Finally, multi-level techniques lack in being efficiently supported, from application-, to architecture-, to circuit-level, in a cohesive cross-layer hierarchy. In this article, we propose Plasticine , a cross-layer methodology for multi-kernel applications, which addresses the aforementioned challenges by efficiently utilizing the synergistic effects of a chain of techniques across layers of abstraction. To this end, we propose an application sensitivity analysis and a heuristic that tailor the precision at constituent kernels of the application by finding the most tolerable degree of approximations for each of consecutive kernels, while also satisfying the ultimate user-defined QoR. The chain of approximations is also effectively enabled in a cross-layer hierarchy, from application- to architecture- to circuit-level, through the plasticity of SIMD multiplier-dividers, each supporting dynamic precision variability along with hybrid functionality. The end-to-end evaluations of Plasticine  on three multi-kernel applications employed in bio-signal processing, image processing, and moving object tracking for Unmanned Air Vehicles (UAV) demonstrate 41%–64%, 39%–62%, and 70%–86% improvements in area, latency, and Area-Delay-Product (ADP), respectively, over 32-bit fixed precision, with negligible loss in QoR. To springboard future research in reconfigurable and approximate computing communities, our implementations will be available and open-sourced at

Mohammed D. Aljubaily ◽  
Imad Alshawi

The existence of a mobile sink for gathering data significantly extends wireless sensor networks (WSNs) lifetime. In recent years, a variety of efficient rendezvous points-based sink mobility approaches has been proposed for avoiding the energy sink-holes problem nearby the sink, diminishing buffer overflow of sensors, and reducing the data latency. Nevertheless, lots of research has been carried out to sort out the energy holes problem using controllable-based sink mobility methods. However, further developments can be demonstrated and achieved on such type of mobility management system. In this paper, a well-rounded strategy involving an energy-efficient routing protocol along with a controllable-based sink mobility method is proposed to extirpate the energy sink-holes problem. This paper fused the fuzzy A-star as a routing protocol for mitigating the energy consumption during data forwarding along with a novel sink mobility method which adopted a grid partitioning system and fuzzy system that takes account of the average residual energy, sensors density, average traffic load, and sources angles to detect the optimal next location of the mobile sink. By utilizing diverse performance metrics, the empirical analysis of our proposed work showed an outstanding result as compared with fuzzy A-star protocol in the case of a static sink.

2022 ◽  
Vol 22 (1) ◽  
pp. 1-30
Rahul Kumar ◽  
Ankur Gupta ◽  
Harkirat Singh Arora ◽  
Balasubramanian Raman

Brain tumors are one of the critical malignant neurological cancers with the highest number of deaths and injuries worldwide. They are categorized into two major classes, high-grade glioma (HGG) and low-grade glioma (LGG), with HGG being more aggressive and malignant, whereas LGG tumors are less aggressive, but if left untreated, they get converted to HGG. Thus, the classification of brain tumors into the corresponding grade is a crucial task, especially for making decisions related to treatment. Motivated by the importance of such critical threats to humans, we propose a novel framework for brain tumor classification using discrete wavelet transform-based fusion of MRI sequences and Radiomics feature extraction. We utilized the Brain Tumor Segmentation 2018 challenge training dataset for the performance evaluation of our approach, and we extract features from three regions of interest derived using a combination of several tumor regions. We used wrapper method-based feature selection techniques for selecting a significant set of features and utilize various machine learning classifiers, Random Forest, Decision Tree, and Extra Randomized Tree for training the model. For proper validation of our approach, we adopt the five-fold cross-validation technique. We achieved state-of-the-art performance considering several performance metrics, 〈 Acc , Sens , Spec , F1-score , MCC , AUC 〉 ≡ 〈 98.60%, 99.05%, 97.33%, 99.05%, 96.42%, 98.19% 〉, where Acc , Sens , Spec , F1-score , MCC , and AUC represents the accuracy, sensitivity, specificity, F1-score, Matthews correlation coefficient, and area-under-the-curve, respectively. We believe our proposed approach will play a crucial role in the planning of clinical treatment and guidelines before surgery.

2022 ◽  
Vol 15 (2) ◽  
pp. 1-27
Andrea Damiani ◽  
Giorgia Fiscaletti ◽  
Marco Bacis ◽  
Rolando Brondolin ◽  
Marco D. Santambrogio

“Cloud-native” is the umbrella adjective describing the standard approach for developing applications that exploit cloud infrastructures’ scalability and elasticity at their best. As the application complexity and user-bases grow, designing for performance becomes a first-class engineering concern. As an answer to these needs, heterogeneous computing platforms gained widespread attention as powerful tools to continue meeting SLAs for compute-intensive cloud-native workloads. We propose BlastFunction, an FPGA-as-a-Service full-stack framework to ease FPGAs’ adoption for cloud-native workloads, integrating with the vast spectrum of fundamental cloud models. At the IaaS level, BlastFunction time-shares FPGA-based accelerators to provide multi-tenant access to accelerated resources without any code rewriting. At the PaaS level, BlastFunction accelerates functionalities leveraging the serverless model and scales functions proactively, depending on the workload’s performance. Further lowering the FPGAs’ adoption barrier, an accelerators’ registry hosts accelerated functions ready to be used within cloud-native applications, bringing the simplicity of a SaaS-like approach to the developers. After an extensive experimental campaign against state-of-the-art cloud scenarios, we show how BlastFunction leads to higher performance metrics (utilization and throughput) against native execution, with minimal latency and overhead differences. Moreover, the scaling scheme we propose outperforms the main serverless autoscaling algorithms in workload performance and scaling operation amount.

Maxim Ziatdinov ◽  
Ayana Ghosh ◽  
Sergei V Kalinin

Abstract Both experimental and computational methods for the exploration of structure, functionality, and properties of materials often necessitate the search across broad parameter spaces to discover optimal experimental conditions and regions of interest in the image space or parameter space of computational models. The direct grid search of the parameter space tends to be extremely time-consuming, leading to the development of strategies balancing exploration of unknown parameter spaces and exploitation towards required performance metrics. However, classical Bayesian optimization strategies based on the Gaussian process (GP) do not readily allow for the incorporation of the known physical behaviors or past knowledge. Here we explore a hybrid optimization/exploration algorithm created by augmenting the standard GP with a structured probabilistic model of the expected system’s behavior. This approach balances the flexibility of the non-parametric GP approach with a rigid structure of physical knowledge encoded into the parametric model. The fully Bayesian treatment of the latter allows additional control over the optimization via the selection of priors for the model parameters. The method is demonstrated for a noisy version of the classical objective function used to evaluate optimization algorithms and further extended to physical lattice models. This methodology is expected to be universally suitable for injecting prior knowledge in the form of physical models and past data in the Bayesian optimization framework.

2022 ◽  
pp. 1-22
Magdalena I. Asborno ◽  
Sarah Hernandez ◽  
Kenneth N. Mitchell ◽  
Manzi Yves

Abstract Travel demand models (TDMs) with freight forecasts estimate performance metrics for competing infrastructure investments and potential policy changes. Unfortunately, freight TDMs fail to represent non-truck modes with levels of detail adequate for multi-modal infrastructure and policy evaluation. Recent expansions in the availability of maritime movement data, i.e. Automatic Identification System (AIS), make it possible to expand and improve representation of maritime modes within freight TDMs. AIS may be used to track vessel locations as timestamped latitude–longitude points. For estimation, calibration and validation of freight TDMs, this work identifies vessel trips by applying network mapping (map-matching) heuristics to AIS data. The automated methods are evaluated on a 747-mile inland waterway network, with AIS data representing 88% of vessel activity. Inspection of 3820 AIS trajectories was used to train the heuristic parameters including stop time, duration and location. Validation shows 84⋅0% accuracy in detecting stops at ports and 83⋅5% accuracy in identifying trips crossing locks. The resulting map-matched vessel trips may be applied to generate origin–destination matrices, calculate time impedances, etc. The proposed methods are transferable to waterways or maritime port systems, as AIS continues to grow.

2022 ◽  
Vol 8 ◽  
Nancy de los Ángeles Segura-Azuara ◽  
Carlos Daniel Varela-Chinchilla ◽  
Plinio A. Trinidad-Calderón

Metabolic dysfunction-associated fatty liver disease (MAFLD), formerly known as nonalcoholic fatty liver disease, is the most prevalent liver disorder worldwide. Historically, its diagnosis required biopsy, even though the procedure has a variable degree of error. Therefore, new non-invasive strategies are needed. Consequently, this article presents a thorough review of biopsy-free scoring systems proposed for the diagnosis of MAFLD. Similarly, it compares the severity of the disease, ranging from hepatic steatosis (HS) and nonalcoholic steatohepatitis (NASH) to fibrosis, by contrasting the corresponding serum markers, clinical associations, and performance metrics of these biopsy-free scoring systems. In this regard, defining MAFLD in conjunction with non-invasive tests can accurately identify patients with fatty liver at risk of fibrosis and its complications. Nonetheless, several biopsy-free scoring systems have been assessed only in certain cohorts; thus, further validation studies in different populations are required, with adjustment for variables, such as body mass index (BMI), clinical settings, concomitant diseases, and ethnic backgrounds. Hence, comprehensive studies on the effects of age, morbid obesity, and prevalence of MAFLD and advanced fibrosis in the target population are required. Nevertheless, the current clinical practice is urged to incorporate biopsy-free scoring systems that demonstrate adequate performance metrics for the accurate detection of patients with MAFLD and underlying conditions or those with contraindications of biopsy.

2022 ◽  
Vol 12 (1) ◽  
Shintaro Sukegawa ◽  
Tamamo Matsuyama ◽  
Futa Tanaka ◽  
Takeshi Hara ◽  
Kazumasa Yoshii ◽  

AbstractPell and Gregory, and Winter’s classifications are frequently implemented to classify the mandibular third molars and are crucial for safe tooth extraction. This study aimed to evaluate the classification accuracy of convolutional neural network (CNN) deep learning models using cropped panoramic radiographs based on these classifications. We compared the diagnostic accuracy of single-task and multi-task learning after labeling 1330 images of mandibular third molars from digital radiographs taken at the Department of Oral and Maxillofacial Surgery at a general hospital (2014–2021). The mandibular third molar classifications were analyzed using a VGG 16 model of a CNN. We statistically evaluated performance metrics [accuracy, precision, recall, F1 score, and area under the curve (AUC)] for each prediction. We found that single-task learning was superior to multi-task learning (all p < 0.05) for all metrics, with large effect sizes and low p-values. Recall and F1 scores for position classification showed medium effect sizes in single and multi-task learning. To our knowledge, this is the first deep learning study to examine single-task and multi-task learning for the classification of mandibular third molars. Our results demonstrated the efficacy of implementing Pell and Gregory, and Winter’s classifications for specific respective tasks.

Sign in / Sign up

Export Citation Format

Share Document