Quantitative Performance Analysis Research Articles

Quantitative performance evaluation of object detectors in hazy environments

We present a quantitative performance analysis of a wide range of state-of-the-art object detection models, such as Mask R-CNN He et al.(2017)[8], RetinaNet Lin et al.(2017)[17] and EfficinetDet Tan et al.(2019)[28] in haze affected environments. This work uses two key performance metrics (Mean Average Precision and Localised Recall Precision) to provide a nuanced view of real world performance of these models in an on-road driving application. Our findings show that the presence of haze further exacerbates the performance differences between single-stage and multi-stage detection models. In addition, not all aspects of the model performance are affected equally. The inclusion of Local Recall Precision (LRP) Oksuz et al.(2018)[21] suggests that more recent models have much improved localisation performance even with similar false negative and false positive results. We also highlight some of the inherent limitations of Neural Network based approaches that could be addressed by Bayesian Neural Networks in the future.

Rising to the Challenge of COVID-19: Pivoting to Online and Project-Based Physiotherapy Student Placements in Contemporary Professional Settings

Online and project-based student placements in sport and corporate settings were incorporated within the Macquarie University Doctor of Physiotherapy following the restriction of face-to-face delivery during the COVID-19 pandemic. This study explores student and educator perceptions of these placements, and analyses student performance results to provide future recommendations. The mixed-methods design included a student survey, semi-structured educator interviews and quantitative analysis of student assessment performance comparing 2020 to 2018/2019 cohorts. Quantitative survey data were described, with proportional differences between groups analysed. Open-ended survey responses and interview transcripts were thematically analysed, and integration of all results was performed. Themes derived from 24 student surveys highlighted that the learning experiences and skills required for online and project-based placements were varied and valuable. Analysis of 176 students’ performance showed differences between performance and applicability of assessment items in 2020 placements in comparison to previous years, although all students met performance requirements. Analysis of eight educator interviews identified that online and project-based placements changed experiences for all stakeholders and highlighted the need for enhanced educator and student communication and organisation for the placement to be successful. Online and project-based placements were considered a better reflection of contemporary work practices, producing valuable deliverables to the business. Three final integrated themes were identified regarding online and project-based elements of placements: learning experiences of students differed, skills for students and educators differed, and placements were representative of real-world work. A hybrid approach that incorporates both online and onsite placement time and includes a project-based component is recommended for future placements. Project-based and online elements provide genuine and valuable learning opportunities for physiotherapy students in preparation for real-world work.

Radio Environment Map Construction Based on Spatial Statistics and Bayesian Hierarchical Model

Constructing an infrastructure for spectrum sensing and spectrum sharing on the cloud is a promising technology. In this paper, we propose an analysis framework based on spectrum data gathered by distributed sensors to construct the radio environment map (REM). To the best of our knowledge, this is the first attempt to leverage the power of Bayesian analysis and Markov chain Monte Carlo (MCMC) in REM. Specifically, a three-stage Bayesian hierarchical model (BHM) is established to imitate the spectrum data generation process under spatially correlated shadow fading. Parameters of BHM are estimated with the MCMC algorithm from data collected by the sensor network. Then, we address the space-dimension spectrum inference problem with the aim to interpolate the signal strength where there is no sensor node by composition sampling. At each point in the area of interest, the posterior predictive distribution of the receive signal strength can be obtained by kernel density smoother. We make spatial inference under two sensor location modes (square lattice located sensors and randomly located sensors) and two scenarios (with and without the information about the signal source), respectively. Simulation results demonstrate that although the randomly located sensors mode is suitable for parameter estimation, the inference performance is not better than the square lattice located sensors mode. Quantitative analysis of the inference performance confirms that the effectiveness of our data analysis framework is compelling.

Image Processing Based Various Strategies of Lung Cancer Diagnosis

Medical imaging represents the utilization of technology in biology for the purpose of noninvasively revealing the internal structure of the organs of the human body. It is a way to improve the quality of the patient’s life through a more precise and rapid diagnosis and with limited side-effects, leading to an effective overall treatment procedure. The main objective of this work is to study the tumour discrimination techniques that cover both micro and macro-scale textures encountered in computed tomography (CT) and digital microscopy (DM) modalities, respectively. Image texture can provide significant information on the (ab) normality of tissue and this work expands this idea to tumour texture grading and classification. The fractal dimension (FD) as a texture measure was applied to contrast enhanced CT lung tumour images in an aim to improve tumour grading accuracy from conventional CT modality, and quantitative performance analysis showed an accuracy of in distinguishing between advanced (aggressive) and early stage (non-aggressive) malignant tumours. A different approach was adopted for subtype discrimination of brain tumour DM images via a set of statistical and model-based texture analysis algorithms.

Elephants evolved strategies reducing the biomechanical complexity of their trunk

The elephant proboscis (trunk), which functions as a muscular hydrostat with a virtually infinite number of degrees of freedom, is a spectacular organ for delicate to heavy object manipulation as well as social and sensory functions. Using high-resolution motion capture and functional morphology analyses, we show here that elephants evolved strategies that reduce the biomechanical complexity of their trunk. Indeed, our behavioral experiments with objects of various shapes, sizes, and weights indicate that (1) complex behaviors emerge from the combination of a finite set of basic movements; (2) curvature, torsion, and strain provide an appropriate kinematic representation, allowing us to extract motion primitives from the trunk trajectories; (3) transport of objects involves the proximal propagation of an inward curvature front initiated at the tip; (4) the trunk can also form pseudo-joints for point-to-point motion; and (5) the trunk tip velocity obeys a power law with its path curvature, similar to human hand drawing movements. We also reveal with unprecedented precision the functional anatomy of the African and Asian elephant trunks using medical imaging and macro-scale serial sectioning, thus drawing strong connections between motion primitives and muscular synergies. Our study is the first combined quantitative analysis of the mechanical performance, kinematic strategies, and functional morphology of the largest animal muscular hydrostat on Earth. It provides data for developing innovative "soft-robotic" manipulators devoid of articulations, replicating the high compliance, flexibility, and strength of the elephant trunk. VIDEO ABSTRACT.

Survey and Performance Analysis of Deep Learning Based Object Detection in Challenging Environments.

Recent progress in deep learning has led to accurate and efficient generic object detection networks. Training of highly reliable models depends on large datasets with highly textured and rich images. However, in real-world scenarios, the performance of the generic object detection system decreases when (i) occlusions hide the objects, (ii) objects are present in low-light images, or (iii) they are merged with background information. In this paper, we refer to all these situations as challenging environments. With the recent rapid development in generic object detection algorithms, notable progress has been observed in the field of deep learning-based object detection in challenging environments. However, there is no consolidated reference to cover the state of the art in this domain. To the best of our knowledge, this paper presents the first comprehensive overview, covering recent approaches that have tackled the problem of object detection in challenging environments. Furthermore, we present a quantitative and qualitative performance analysis of these approaches and discuss the currently available challenging datasets. Moreover, this paper investigates the performance of current state-of-the-art generic object detection algorithms by benchmarking results on the three well-known challenging datasets. Finally, we highlight several current shortcomings and outline future directions.

L₁-Adaptive Robust Control Design for a Pressurized Water-Type Nuclear Power Plant

This work proposes adaptive control-based design strategies to control a pressurized water reactor (PWR) nuclear power plant (NPP). An L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -adaptive-based state-feedback control technique is proposed using the linear quadratic Gaussian control and projection-based adaptation laws. The control scheme possesses good robustness capabilities in handling disturbances and uncertainties. A robust L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -adaptive control technique is also proposed by combining the L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -adaptive control with the loop transfer recovery (LTR) technology. The framework hence gives the strengthened robust set-point tracking performance given the matched and unmatched uncertainties and disturbances. The NPP model employed in this article is defined by five inputs, five outputs, and 38 state variables. A linear model for controller design is obtained by linearizing the nonlinear NPP model at operating conditions. Various simulations are carried out on subsystems of the NPP to verify the effectiveness of the proposed scheme. Numerical and statistical measures are computed for quantitative analysis of the controllers' performance. Several classical control design techniques are also implemented, and their performance is compared with the proposed adaptive control techniques.

Standard units for ElectroChromic Shift measurements in plant biology.

The absorbance shift of pigments is proportional to the membrane potential (Δψ) in plants, green algae, and many photosynthetic bacteria. It is currently denoted as ElectroChromic Shift (ECS) at 515-520 nm for plant carotenoids. It is increasingly being used for phenotyping plants for traits related to photosynthesis or chloroplast metabolism because it is a non-invasive technique and also because more instruments are now commercially available from various manufacturers. The ECS technique is currently used to monitor the post-illumination decay of the proton-motive force (pmf), but it has a more general use for quantitative studies on photosynthetic energy transduction. Here we briefly summarize the basic knowledge on ECS, emphasize the full potential of this technique, and propose a quantitative analysis of the photosynthetic performance with the definition of a transmission coefficient for electrons along the photosynthetic chain.

Determining thermo-mechanical stress sources of an integrated optical device

In this study, we analyze the thermo-mechanical behavior of a multi-functional integrated optical chip (MIOC) via the finite element method (FEM). MIOC is a kind of fiber optic component which has a high thermal sensitivity. So; during temperature changes its mechanical resistance has a considerable critical significance. To investigate the thermo-mechanical effects, a three-dimensional device structure is modeled and time-dependent Von-Mises stress analyses are carried out via the multiphysics approach in the simulation environment. The simulation results are evaluated regarding the change of the crystal structure, epoxy layers, and waveguide core region. It is demonstrated that structural configuration has a crucial impact on the mechanical stability of the integrated optical device. Because of this reason, case D is accepted as a preferable geometrical structure for mass production. Also, the most dominant stress effect arises from the epoxy layer interface between the fiber pigtail carrier and lithium niobate (LiNbO3) chip called region 1. In this context, we investigate the influence of extreme thermal conditions on the induced stress on region 1. Apart from the mechanical strength of the devices, optical transmission is another subject to consider. Two claims arise on this point: power flow through the waveguide core is temperature-dependent and it is also related to the stress-optical effect. Finally, we compare the simulation results with the experimental results and there is certainly a consistency between the two separate analyses. Furthermore; it can be said that manufacturing more than 500 devices facilitates the quantitative analysis of device performance.

Quantitative analysis of real-time performance and hardware requirements for edge computing platform

Quantitative analysis of real-time performance and hardware requirements for edge computing platform

Goal Blending for Responsive Shared Autonomy in a Navigating Vehicle

Human-robot shared autonomy techniques for vehicle navigation hold promise for reducing a human driver’s workload, ensuring safety, and improving navigation efficiency. However, because typical techniques achieve these improvements by effectively removing human control at critical moments, these approaches often exhibit poor responsiveness to human commands—especially in cluttered environments. In this paper, we propose a novel goal-blending shared autonomy (GBSA) system, which aims to improve responsiveness in shared autonomy systems by blending human and robot input during the selection of local navigation goals as opposed to low-level motor (servo-level) commands. We validate the proposed approach by performing a human study involving an intelligent wheelchair and compare GBSA to a representative servo-level shared control system that uses a policy-blending approach. The results of both quantitative performance analysis and a subjective survey show that GBSA exhibits significantly better system responsiveness and induces higher user satisfaction than the existing approach.

Maximizing selectivity: An analysis of isoporous membranes

Membranes are compelling candidates for many separation-based industrial processes. However, all synthetic membranes are subject to well-recognized permeability-selectivity trade-offs that hinder their use in advanced applications. Having uniform nanoscale pore size, isoporous nanofiltration and ultrafiltration membranes have attracted wide research interest. However, quantitative analysis of isoporous membrane performance is lacking – particularly at module and system-level scales. In this study, an analytical model is built to investigate how membrane pore-size distribution affects the solute separation efficiency (i.e., rejection and selectivity). The model accounts for convective hindrance as well as concentration polarization and explores effects on separation from the solute-to-pore-size ratio and percent recovery (i.e., fraction of feed flow that passes through the membrane). At the module level, our analysis suggests that a notably sharper rejection vs. solute size curve can be obtained as the pore-size distribution becomes narrower. As the recovery increases, the rejection of a solute is maintained at a high level using isoporous membranes while the rejection drops rapidly for membranes that possess a disperse pore-size distribution. Furthermore, in the separation of mixed solutes, isoporous membranes achieve a large selectivity with a modest loss of permeability. Overall, this study elaborates the unique role that isoporous membranes play within the permeability-selectivity trade-off relations and identifies the most exciting opportunities for their future applications.

Effects of market orientation, innovation strategies and value-based pricing on market performance

PurposeThis study aims to propose and test a theoretical model that contemplates antecedent constructs of organizational performance, as well as the interaction among them.Design/methodology/approachA survey was conducted with 151 Brazilian exclusive stores in the planned furniture segment. The data analysis was performed using two statistical techniques, focused on hierarchical regression and mediation and moderation tests.FindingsAmong the main results of the survey are the direct and significant effects of value-based pricing and innovation strategies and the indirect effect of market orientation on market performance. As for moderation, the authors identified that profitability moderates the relationship between value-based pricing and market performance, and the degree of sales projection moderates the relationship between market orientation and market performance.Originality/valueThe insertion of value-based pricing as a variable in quantitative analysis of market performance meets the lack of academic research. When the constructs are combined or interacted with each other, they have a stronger and more significant effect on performance. In addition, this work proposes two moderating variables that can interfere in the relationship between the analyzed constructs (profitability and sales projection). It was identified that the relationships between the constructs and that the orientation towards the market (despite not directly impacting market performance) interfere with the relationship based on mediation of variable innovation strategies and value-based pricing.

Cultural events for a sustainable tourism development in urban destinations: the case of Milan’s week

Purpose of the paper: The aim of this paper is to explore the effects generated by a suite of cultural micro-medium events in an urban destination on both hotels’ performance and the seasonality structure in order to promote sustainable tourism development. Methodology: The empirical analysis uses a mixed method that combines a quantitative analysis of the daily performance of a destination with a desk analysis of press interviews to local stakeholders. Findings: The results highlight a positive contribution of cultural micro-medium events to tourism at the destination. This evidence contributes to the academic debate on strategic event management by shedding light on the potential role of minor cultural events as a driver for sustainable tourism development. Practical implications: This study suggests guidelines to destination managers on how to benefit from micro-medium cultural events: a strong connection with the destination’s vocations, the importance of public-private collaboration and the establishment of a portfolio of recurrent events. Limitations of the research: This explorative study presents two main limitations: the authors cannot exclude that other small events were taking place in the city at the same time as the micro-medium cultural events analysed. Secondly, several of the events studied are recent and therefore their impact on the destination could be underestimated. Originality of the paper: During the last decades, the managerial literature has been devoting considerable attention to the role and the benefits generated by events. However, the main focus of these studies has been on large and mega events while little consideration has been dedicated to smaller events which are widespread, recurrent and relatively easier to manage.

Molten Pool Tracking Using a Superpixel-Based Approach in a Laser Metal Deposition Process

Abstract Nowadays, additive manufacturing technologies (AM) suffer from insufficient or lacking methodologies/techniques for quality control. This fact represents a key technological barrier preventing broader industrial adoption of AM, particularly in high-value applications where component failure cannot be accepted. This article presents a real-time melt pool segmentation and monitoring technique applicable to the direct laser metal deposition (LMD) process. An infrared camera with an InSb detector (resolution of 640 × 480, spectral range between 3 and 5 μm) was used. An algorithm, called gravitational superpixels, is presented. This algorithm can group pixels and generate superpixels based on a block generation technique that compares color similarity and temperature in infrared images. Besides, a color similarity correction is applied to reduce uncertainty in segmentation, as well as for eliminating the image background. The task of extracting edges is based on the law of universal gravitation. A quantitative and qualitative algorithm performance analysis, which uses standard metrics, is presented. The analysis demonstrates better versatility than reduction/feature extraction or image segmentation approaches by high-/low-pass filtering. The experimental validation was carried out, extracting and measuring the molten pool geometry and its thermal signature. Then, measures were compared against ground truth and against results obtained by other similar methods. The proposed gravitational superpixel method has higher precision and performance. Our proposal has a significant potential for monitoring industrial AM processes since it requires minimal modifications of commercially available industrial machines.

Clinical analysis of video recordings of the basic motor patterns (CLAVIR) for the assessment of movement disorders in children and adolescents with acute lymphoblastic leukemia

Movement disorders arising in pediatric patients with acute lymphoblastic leukemia (ALL) during treatment require a more differentiated approach to diagnosis and the choice of rehabilitation methods. The aim of this study was to investigate the conceptional structure of supine-to-stand (STS) transition patterns and to develop a method for the diagnosis of movement disorders and the assessment of the effectiveness of medical rehabilitation in children and adolescents with ALL. We carried out a prospective comparative non-randomized study. The study was approved by the Independent Ethics Committee and the Scientific Council of the Dmitry Rogachev National Medical Research Center of Pediatric Hematology, Oncology and Immunology of Ministry of Healthcare of the Russian Federation. The study included 184 children who were assigned to three groups. Group 1 (study group) included patients with ALL treated at the Center (n = 48, the median age was 14.0 years). Group 2 (control group) included patients with various serious diseases (acute myeloid leukemia, primary immunodeficiency, CNS malignancies, bone tumors, etc.) who also underwent treatment at the Center (n = 69, the median age was 14.5 years). Group 3 (control group) included healthy children and adolescents (n = 67, the median age was 14.2 years). We analyzed the characteristics of video recordings of the supine-to-stand process in apparently healthy children (Group 3) and in the patients treated at the Center (Groups 1 and 2) and then performed comparative analysis. We managed to detect, document, and divide into phases the video-based criteria of invariant characteristics of the acyclic locomotor pattern of the STS movement (from a supine to standing position with both feet on the floor). We identified the STS movement phases and clinically significant variants of STS transition patterns which were easily detectable on the video recordings. The objectivity of the analysis of the video-based criteria of invariant characteristics of the STS movement was achieved by the registration of timing characteristics of the locomotion pattern phases on video recordings. By calculating the coefficients of variation for observations from different angles and inter-researcher variability, we detected the most representative phases of the STS movement pattern on video recordings. A quantitative analysis of the STS test performance revealed significant differences between healthy controls and children with oncological diseases. The clinical analysis of video recordings of the basic motor patterns (CLAVIR) contributes a substantial amount of objective data to the clinical assessment of the diagnostic supine-to-stand test results in children and adolescents treated for ALL.

Study on Test Method of Automatic Stopping Performance of Liquid Stop Membrane for Infusion Set

At present, there is no guidance or standard document to evaluate the performance of liquid stop membrane for infusion set, and it is impossible to conduct quantitative analysis and quality supervision of product performance. In this paper, a method for measuring bubble point pressure of liquid stop membrane is studied, and the correlation between bubble point pressure and the performance of liquid stop membrane is explored. The results of bubble point pressure test are used as the daily control index of liquid stop performance. It provides a practical reference value for the evaluation of liquid stopping performance of liquid stop membrane.

Dehazing of Satellite Images using Adaptive Black Widow Optimization-based framework

ABSTRACT Haze is a common atmospheric disturbance that adversely affects the quality of optical data, thus often restricting their usability. Since these effects are inherent in the process of spaceborne Earth sensing, it is important to develop effective methods to remove them. This work proposes a novel method for de-hazing satellite imagery and outdoor camera images. It is developed by modifying the transmission map used in Dark Channel Prior (DCP) method. A Weighted Variance Guided Filter (WVGF) is introduced for enhancing the image quality, which included a two-stage image decomposition and fusion process. The method also optimally combines the radiance and transmission components along with an additional stage modelling a fusion-based transparency function. A final guided filter-based image refinement scheme is incorporated to improve the processed image quality. The optimal tuning of the image-dependent parameters at various stages is achieved using the newly proposed Adaptive Black Widow Optimization (ABWO) algorithm, which makes the proposed de-hazing scheme fully automatic. Qualitative and quantitative performance analyses, and the results are compared with other state-of-the-art methods. The experimental results reveal that the proposed method performs better as compared with others, independent of the haze density, without losing the natural look of the scene.

Injury Risk Prediction of Aerobics Athletes Based on Big Data and Computer Vision

In recent years, competitive aerobics has been rapidly popularized and developed, and the level of sports skills has also been greatly improved. The performance of some events has gradually approached and reached the advanced level. Therefore, it is vital to invest in the quantitative analysis and cross-disciplinary comprehensive research of aerobics performance and related factors. This paper adopts big data analysis technology and computer vision technology based on convolutional neural network, according to the related theories of sports biomechanics and computer image recognition, to establish a loss risk prediction model for aerobics athletes. The approach firstly has used technology of big data analysis for analyzing the characteristics of competitive aerobics sports data. Secondly, the approach combines the convolutional neural network to visually recognize the aerobics sports images and establish a two-branch prediction model. Finally, the output can be fused to accurately diagnose and evaluate the level of physical fitness development of aerobics athletes, the focus and goal of training content are clarified, and the scientific degree of aerobics training is improved. The study can help injury risk prediction of aerobic athletes based on applications of big data and computer vision.

A Tutorial on General Air-Gap Field Modulation Theory for Electrical Machines

This tutorial paper presents the mathematics behind the widely observed air-gap field modulation phenomena in electrical machines and derives the duality between electrical machines and switching converters. A bibliometric analysis of the existing research on various machine types is presented to show the historical development of electrical machines from the perspective of the number of publications, showing the necessity and urgency of unifying the analysis of operating principles/torque production mechanisms before the development of the general air-gap field modulation theory in 2017. The theoretical framework and its applications are reviewed. Detailed examples of how to use the developed theory to analyze the operating principle/torque production, conduct the quantitative analysis of parameters and basic performance, and make innovations from topologies of typical electrical machines are also included for verification as well as self-study.