Quantitative Performance Evaluation Research Articles

Quantitative Evaluation of Seismic Performance for Truss Structures Based on the Condition Number of Dynamic Matrix

The quantitative analysis of seismic performance under small and moderate earthquakes is of great significance. However, only using the stiffness distribution index is no longer applicable to seismic performance evaluation, and the influence of mass distribution must be introduced. In this study, under the action of small and medium earthquakes, the equation of motion can be simplified into the equilibrium equation of the dynamic matrix by the quasi-static method. Furthermore, a condition number index of dynamic matrix is proposed to evaluate the seismic performance of truss structures, which can consider both stiffness distribution and mass distribution. Then, the correctness of the proposed index is verified by comparing with the displacement and strain indexes. In addition, the performance of truss structure is studied by the condition number of stiffness matrix, mass matrix and dynamic matrix. It is found that since the condition number of stiffness matrix and the condition number of mass matrix cannot consider both stiffness and mass, it is not comprehensive to use these two indexes to evaluate the seismic performance of truss structures. The evaluation result based on the condition number of dynamic matrix is more reasonable under small and medium earthquakes.

Impacts of architectural beauty to building energy performance

Consideration of architectural beauty in the built environment is growing as the broader concept of sustainable design replaces the more narrowly defined concepts of high performance or green building. This work is a part of Beauty in Building (BiB) research conducted by a team of architects and engineers working to understand links between architectural beauty and building performance. This work presents the exploration findings on what impact architectural beauty may have on building energy performance. A sample of 35 case studies contrasting high performing buildings with architecturally beautiful and high performing buildings was evaluated using the developed BiB matrix. Features that distinguished the best performing buildings from the rest of the sample population were identified based on the results of the case study evaluation. Building energy models representing these building features were then developed for quantitative evaluation of energy performance through energy simulation. Relative importance to beauty and energy performance of each of the features was determined and presented as weighting factors. The results illustrate those features that exhibited density, a combination of multiple systems, in the designs offered better performance relative to both beauty and energy.

Full-field in vivo imaging of nanoparticles using benchtop cone-beam XFCT system with pixelated photon counting detector

Objective. X-ray fluorescence computed tomography (XFCT) is a promising noninvasive technique for in vivo imaging of high-Z elements (e.g. gadolinium (Gd) or gold (Au)). In this study we upgraded our experimental XFCT system using a flat panel photon counting detector with redesigned pinhole collimation in order to achieve 3D XFCT images during one scan. Approach. Aiming at the characteristics of pinhole-collimated cone-beam XFCT imaging, a new scatter correction algorithm was proposed to estimate the normalized spectrum of scatter background based on K–N formula and realize correction by a weighted least squares method. Then, images were quantitatively reconstructed by a maximum likelihood iterative algorithm with the attenuation correction. Main results. The potential on full-field in vivo XFCT imaging of this new system was investigated. An imaging experiment of a PMMA phantom with the diameter of 35 mm was carried out for quantitative evaluation of the system performance. Results show that 2 mg ml−1 Gd solutions can be successfully reconstructed with a 45 min cone-beam XFCT scan. In vivo XFCT imaging experiments of mice with injection of Gd nanoparticles (GdNPs) were also performed and demonstrated in this paper. A mouse was injected through the tail vein with 20 mg ml−1 NaGdF4 solution and then anesthetized with isoflurane during the cone-beam XFCT scan. Significance. The distribution of the GdNPs inside the mouse can be well reconstructed so that the deposition of NPs in vivo can be clearly observed, which indicates the feasibility of the proposed system for full-field XFCT of small animals and further potential in relevant in vivo research.

DoLP and AoP Synthesis from division of focal plane polarimeters using CycleGAN

Division of focal plane (DoFP) polarimeter brings significant advantages for capturing polarization information, and its unique structure enables temporal synchronization of polarization intensity measurements across scenes. While DoFP can obtain polarization information in all four directions simultaneously, it also reduces the spatial resolution of the image to 1/4 of the camera resolution. In order to solve low resolution and the cumulative error caused by the formula calculation. Using CycleGAN to construct a raw mosaic image-to-polarization properties images model, which differs from general interpolation methods and other existing deep learning methods with paired datasets and takes microgrid images as input and outputs the degree of linear polarization (DoLP) and angle of polarization (AoP) directly by learning the mapping function between unpaired the mosaic images and the polarization properties. In addition, Gradient Magnitude Similarity Deviation (GMSD) metric is applied to preserve satisfactory reconstructed image edge contour information and reduce IFOV artifacts and aliasing. The experimental results demonstrate that the quantitative performance evaluation metrics scores of our method are all higher than other methods and the reconstructed DoLP and AoP images are comparable to the ground truth imagery in terms of visual quality. The end-to-end network structure trained on unpaired datasets solves the severe limitations of paired datasets training, is more suitable for DoLP and AoP reconstructing.

An Artificial Intelligence-as-a-Service Architecture for deep learning model embodiment on low-cost devices: A case study of COVID-19 diagnosis

Coronavirus Disease-2019 (COVID-19) causes Severe Acute Respiratory Syndrome-Corona Virus-2 (SARS-CoV-2) and has opened several challenges for research concerning diagnosis and treatment. Chest X-rays and computed tomography (CT) scans are effective and fast alternatives to detect and assess the damage that COVID causes to the lungs at different stages of the disease. Although the CT scan is an accurate exam, the chest X-ray is still helpful due to the cheaper, faster, lower radiation exposure, and is available in low-incoming countries. Computer-aided diagnostic systems based on Artificial Intelligence (AI) and computer vision are an alternative to extract features from X-ray images, providing an accurate COVID-19 diagnosis. However, specialized and expensive computational resources come across as challenging. Also, it needs to be better understood how low-cost devices and smartphones can hold AI models to predict diseases timely. Even using deep learning to support image-based medical diagnosis, challenges still need to be addressed once the known techniques use centralized intelligence on high-performance servers, making it difficult to embed these models in low-cost devices. This paper sheds light on these questions by proposing the Artificial Intelligence as a Service Architecture (AIaaS), a hybrid AI support operation, both centralized and distributed, with the purpose of enabling the embedding of already-trained models on low-cost devices or smartphones. We demonstrated the suitability of our architecture through a case study of COVID-19 diagnosis using a low-cost device. Among the main findings of this paper, we point out the performance evaluation of low-cost devices to handle COVID-19 predicting tasks timely and accurately and the quantitative performance evaluation of CNN models embodiment on low-cost devices.

Monocular Depth Estimation of Old Photos via Collaboration of Monocular and Stereo Networks

Old photos that were captured about a century ago have archaeological and historical significance. Many of the old photos have been successfully digitized, but most of them suffer from severe and complicated distortion. Thus, prior studies have focused on image restoration tasks such as denoising, inpainting, and colorization. In this paper, we pay attention to the depth estimation of old photos, enabling a more enjoyable appreciation of them and helping better understand past human life, activities, and environments. Because most old photos are available as single-view images, monocular depth estimation techniques can be considered a solution. However, most high-performance techniques are based on supervised learning, which requires ground-truth depth maps. Because this kind of supervised learning is not feasible for old photos, in this paper, we present a learning framework that finetunes a pretrained monocular depth estimation network for each old photo. Specifically, the pretrained monocular depth estimation network predicts stereo depth maps for stereo image rendering. Then, the pretrained stereo network predicts depth estimates from the rendered stereo image pair. By extracting reliable depth estimates and using them for supervision of the monocular network, the monocular network can be gradually learned to produce a high-quality depth map of the given old photo. From the qualitative and quantitative performance evaluations on old photos, we demonstrate the effectiveness of the proposed method.

Using Particle Residence Time Distributions as an Experimental Approach for Evaluating the Performance of Different Designs for a Pilot-Scale Spray Dryer

The performances of four different designs for a pilot-scale spray dryer have been evaluated and compared based on experimentally measured particle residence time distributions (RTD), recovery rates and physical properties of spray-dried fresh skim milk. The RTDs have been measured using a dye pulse injection method, and the measurements have been fitted to models using continuous stirred-tank reactors in series (CSTR-TIS) for quantitative performance evaluation and comparison. Conical drying chambers and a box connection design have been used in the latest dryer design to reduce the amount of wall deposition and provide a smoother gas flow pattern. The particle-to-gas mean residence time ratio for the latest design is significantly closer to unity (1.6 s/s to 1.0 s/s) compared with earlier designs (2.6 s/s to 1.5 s/s). The latest design has a wider spread of RTD (n = 5–8) compared with earlier designs (n = 13–18), which may be linked to the recirculation zone in the box connection. Although the latest design has a wider spread of RTD, the conical design has shown promising results compared with a cylindrical drying chamber in terms of overall wall deposition behaviours.

Performance Evaluation of Uncooled UAV Infrared Camera in Detecting Concrete Delamination

Concrete delamination detection using unmanned aerial vehicle (UAV)-mounted infrared cameras has proved effective in recent research. However, most studies used expensive research-grade infrared cameras and proprietary software to acquire images, which is hard to implement in state departments of transportation (DOTs) due to the lack of specialty professionals. Some state DOTs started deploying lightweight UAV-based consumer-grade infrared cameras for delamination detection. Quantitative performance evaluation of such a camera in concrete delamination detection is lacking. To fill this gap, this study intends to conduct a comprehensive assessment of the consumer-grade camera benchmarked against the results of a research-grade camera to see the practicality of using the small and low-cost camera in concrete delamination detection. Data was collected for a slab with mimicked delamination and two in-service bridge decks. For the case of the slab, maximum detectability of 70–72% was achieved. A transient numerical simulation was conducted to provide a supplemental and noise-free dataset to explore detectability accuracy peaks throughout the day. The results of the in-service bridge decks indicated that the consumer-grade infrared camera provided adequate detection of the locations of suspected delamination. Results of both the slab and in-service bridge decks were comparable to those of a research-grade infrared camera.

An NMF-based method for jointly handling mixture nonlinearity and intraclass variability in hyperspectral blind source separation

Considering a set of observed signals that result from mixing (i.e. combining) a set of unknown source signals by means of an unknown function, blind source separation (BSS) and blind mixture identification (BMI) methods aim at estimating these source signals and/or the mixing function. Such methods have been extensively used, e.g. to process hyperspectral data in the field of remote sensing (i.e. Earth observation). However, most of these methods are restricted to the simplest mixing model, namely linear mixtures without the “variability” defined below. Some investigations started to tackle the more complex case of linear-quadratic (LQ), i.e. second-order polynomial, and memoryless mixtures. Some other investigations deal with the so-called intraclass variability phenomenon, i.e. with the case when each source yields a component having a somewhat different “shape” in each observed signal. Such nonlinearity and variability may e.g. appear in remote sensing hyperspectral images, as detailed in this paper. To our knowledge, each BSS/BMI method from the literature related to the nonlinearity and variability issues only addresses one of them. In contrast, we here propose a more powerful, very generic, BSS/BMI approach, that extends standard Nonnegative Matrix Factorization so as to jointly handle LQ mixtures and arbitrary source intraclass variability. This opens the way to a much wider range of BSS/BMI applications than plain linear “variabilityless” mixtures, e.g. to handle the above-defined two issues of remote sensing. Considering the latter application, we built data sets so that they are both realistic and suited to a detailed quantitative performance evaluation. The tests reported in this paper show that our method significantly outperforms several approaches from the literature: the estimation errors are thus decreased by factors up to around 2 and 1.5, respectively for spectra and mixing coefficients.

NIMG-25. OPTIMIZATION OF ARTIFICIAL INTELLIGENCE ALGORITHMS FOR LOW-RESOURCE/CLINICAL ENVIRONMENTS: FOCUS ON CLINICALLY-RELEVANT GLIOMA REGION DELINEATION

Abstract BACKGROUND Diffuse astrocytic glioma are common and aggressive malignant primary brain tumors with grim prognosis. Artificial intelligence (AI) has shown promise across predictive, prognostic, and diagnostic neuro-oncology applications, towards improving patient management. However, clinical translation and deployment are hampered by AI models’ requirements for explicit acceleration cards, which are not typically considered in clinical environments. Here, we seek the execution of AI models in such clinical/low-resource environments, facilitated by mathematical optimizations rather than investing in acceleration cards, and focus on the use case of delineating clinically-relevant regions, namely the entire tumor burden (ETB) and tumor core (TC). METHODS We identified the BraTS20 retrospective cohort of 369 glioma cases, each described by 4 structural multi-parametric MRI (mpMRI) scans (T1,T1Gd,T2,T2-FLAIR). The Generally Nuanced Deep Learning Framework (GaNDLFv0.0.14/PyTorchv1.8.2) was used to train the original AI model (ResUNet), by randomly sampling 40 643 patches from each mpMRI scan. We then investigate the contributions of post-training mathematical optimizations. Quantitative performance evaluation of the original and optimized (GaNDLFv0.0.14/OpenVINOTM-INT8-v2022.1.0) models were based on 125 unseen hold-out cases (BraTS20 validation dataset), using the dice similarity coefficient (DSC), while profiling in a consumer-grade workstation, i.e., typical clinical hardware configuration. RESULTS Negligible delineation performance differences were observed between the original and optimized AI models, for both ETB (DSCoriginal/DSCoptimized= 0.877/0.876) and TC (DSCoriginal/DSCoptimized= 0.773/0.772). However, the optimized model yielded substantial improvements in latency (up to 5.4x faster inference) and 53% less memory footprint. CONCLUSIONS Post-training mathematical optimization of AI models yields substantial gains in latency and memory usage, while maintaining their accuracy. Although we focused on delineation, we anticipate these mathematical optimizations to be applicable in other AI models. Post-training optimization is a promising approach for deploying AI models on consumer-grade CPUs, and hence facilitating their translation in low-resource/clinical environments, potentially contributing to improved patient management, treatment decisions, and response assessment. *author Siddhesh Thakur is an equal contributing first author.

The Hidden Burden: Qualitative Differences in How URiM Students Experience the Clinical Microenvironment

It is well documented that medical students who identify as underrepresented in medicine are more likely to encounter social challenges in the clinical environment. Successful navigation of these challenges requires a social and emotional agility that is unmeasured in traditional metrics of success. The effects of this requirement has not yet been explored. The authors therefore set out to investigate the variations in experiences that exist between underrepresented minority students in medicine (URiM) and white students, and to determine if there was a difference in the quantitative performance evaluations applied to both groups of students. This was a mixed-methods study. In the quantitative portion, the authors retrospectively analyzed the standardized patient encounter scores of medical students from a single medical school in Michigan during the years of 2016 to 2018. The authors used multivariable ordinary least squares regression models to evaluate the differences in scores by race. In the qualitative portion, students volunteered to be interviewed and self-identified their race and gender. The authors employed semi-structured interview techniques to gather information about how the student felt their cultural or ethnic background affected their experience in the clinical environment. For the quantitative portion of this study, the authors analyzed the scores of 534 students over 4 different standardized patient encounters. The average score across all 4 standardized patient encounters was 88.7 (SD=5.6). The average score across all 4 standardized patient encounters for white students was 89 (SD=5.3), Black 87.9 (SD=7.4) Twenty-four students participated in the semi-structured interviews. Participants described feeling that the way their assessors interacted with them was largely affected by their race or gender. They also described feeling tension between how they would usually express themselves and how they were expected to in the clinical environment. When probed further, participants described various methods of adaptation to this tension including changing their hair or natural style of speech and modifying their perception of their role in the clinical environment.

Survival Prediction of Glioma Patients from Integrated Radiology and Pathology Images Using Machine Learning Ensemble Regression Methods

Gliomas are tumors of the central nervous system, which usually start within the glial cells of the brain or the spinal cord. These are extremely migratory and diffusive tumors, which quickly expand to the surrounding regions in the brain. There are different grades of gliomas, hinting about their growth patterns and aggressiveness and potential response to the treatment. As part of routine clinical procedure for gliomas, both radiology images (rad), such as multiparametric MR images, and digital pathology images (path) from tissue samples are acquired. Each of these data streams are used separately for prediction of the survival outcome of gliomas, however, these images provide complimentary information, which can be used in an integrated way for better prediction. There is a need to develop an image-based method that can utilise the information extracted from these imaging sequences in a synergistic way to predict patients’ outcome and to potentially assist in building comprehensive and patient-centric treatment plans. The objective of this study is to improve survival prediction outcomes of gliomas by integrating radiology and pathology imaging. Multiparametric magnetic resonance imaging (MRI), rad images, and path images of glioma patients were acquired from The Cancer Imaging Archive. Quantitative imaging features were extracted from tumor regions in rad and path images. The features were given as input to an ensemble regression machine learning pipeline, including support vector regression, AdaBoost, gradient boost, and random forest. The performance of the model was evaluated in several configurations, including leave-one-out, five-fold cross-validation, and split-train-test. Moreover, the quantitative performance evaluations were conducted separately in the complete cohort (n = 171), high-grade gliomas (HGGs), n = 75, and low-grade gliomas (LGGs), n = 96. The combined rad and path features outperformed individual feature types in all the configurations and datasets. In leave-one-out configuration, the model comprising both rad and path features was successfully validated on the complete dataset comprising HGFs and LGGs (R=0.84 p=2.2×10−16). The Kaplan–Meier curves generated on the predictions of the proposed model yielded a hazard ratio of 3.314 [95%CI:1.718−6.394], log−rank(P)=2×10−4 on combined rad and path features. Conclusion: The proposed approach emphasizes radiology experts and pathology experts’ clinical workflows by creating prognosticators upon ‘rad’ radiology images and digital pathology ‘path’ images independently, as well as combining the power of both, also through delivering integrated analysis, that can contribute to a collaborative attempt between different departments for administration of patients with gliomas.

Energy Management Simulation with Multi-Agent Reinforcement Learning: An Approach to Achieve Reliability and Resilience

The share of energy produced by small-scale renewable energy sources, including photovoltaic panels and wind turbines, will significantly increase in the near future. These systems will be integrated in microgrids to strengthen the independence of energy consumers. This work deals with energy management in microgrids, taking into account the volatile nature of renewable energy sources. In the developed approach, Multi-Agent Reinforcement Learning is applied, where agents represent microgrid components. The individual agents are trained to make good decisions with respect to adapting to the energy load in the grid. Training of agents leverages the historic energy profile data for energy consumption and renewable energy production. The implemented energy management simulation shows good performance and balances the energy flows. The quantitative performance evaluation includes comparisons with the exact solutions from a linear program. The computational results demonstrate good generalisation capabilities of the trained agents and the impact of these capabilities on the reliability and resilience of energy management in microgrids.

A virtual platform of electrical tomography for multiphase flow imaging

This paper reports a new approach to quantitatively evaluate the performance of Electrical Tomography (ET) in measuring dynamic multiphase flows. A virtual multiphase flow imaging platform based on ET is constructed and demonstrated on two typical gas–liquid flows, i.e., water–gas flow and oil–gas flow. Two coupling simulation cases, i.e., water–gas flow field and electric currents field coupling simulation and oil–gas flow field and electrostatics field coupling simulation, are performed to simulate multiphase flow sensing of Electrical Impedance Tomography (EIT) and Electrical Capacitance Tomography (ECT). We quantitatively evaluated the representative EIT and ECT image reconstruction algorithms on the virtual evaluation platform bringing evidence of the improved capability to capture the key flow features of the fluid mixture with respect to traditional static phantoms. Ad-hoc treatment of the signal noise enables one to better capture dynamic responses of the fluid phase volume fractions and their spatial gradients throughout their mixing along the conduit, ultimately demonstrating unprecedented potential in the quantitative characterization of complex, unsteady multi-phase systems. The proposed image reconstruction constitutes a highly effective platform for quantitative performance evaluation of ET, parameter optimization of model-based ET image reconstruction algorithms, and for the development of data-driven ET algorithms in multiphase flow imaging.

Digitally-enhanced lubricant evaluation scheme for hot stamping applications

Digitally-enhanced technologies are set to transform every aspect of manufacturing. Networks of sensors that compute at the edge (streamlining information flow from devices and providing real-time local data analysis), and emerging Cloud Finite Element Analysis technologies yield data at unprecedented scales, both in terms of volume and precision, providing information on complex processes and systems that had previously been impractical. Cloud Finite Element Analysis technologies enable proactive data collection in a supply chain of, for example the metal forming industry, throughout the life cycle of a product or process, which presents revolutionary opportunities for the development and evaluation of digitally-enhanced lubricants, which requires a coherent research agenda involving the merging of tribological knowledge, manufacturing and data science. In the present study, data obtained from a vast number of experimentally verified finite element simulation results is used for a metal forming process to develop a digitally-enhanced lubricant evaluation approach, by precisely representing the tribological boundary conditions at the workpiece/tooling interface, i.e., complex loading conditions of contact pressures, sliding speeds and temperatures. The presented approach combines the implementation of digital characteristics of the target forming process, data-guided lubricant testing and mechanism-based accurate theoretical modelling, enabling the development of data-centric lubricant limit diagrams and intuitive and quantitative evaluation of the lubricant performance.

Enhanced design of PID controller and noise filter for second order stable and unstable processes with time delay

Abstract In this work, a PID controller along with a noise filter is designed using direct synthesis method for second order stable and unstable processes with time delay. Proposed method involves a single design parameter λ whose value need to be adjusted such that a desired balance between performance and robustness of the system is achieved. Guidelines to select suitable values of λ based on the maximum sensitivity values are provided. Various computer simulations are performed in presence of measurement noise on stable, unstable, integrating and double integrating dynamic systems to illustrate the advantages of suggested control method over some contemporary techniques. Performance measures (integral absolute error and integral squared error) and robustness measures such as maximum sensitivity (M s), complimentary sensitivity (M t) are calculated for the quantitative performance evaluation of the proposed tuning strategy. The suggested tuning algorithm is simple and it yields improved closed loop response compared to some reported methods, satisfactory robustness and smooth control action in presence of noise.

Bioretention soil capacity for removing nutrients, metals, and polycyclic aromatic hydrocarbons; roles of co-contaminants, pH, salinity and dissolved organic carbon

Conventional bioretention soil media (BSM: e.g., loamy sand) is employed in infiltration-based stormwater management practices, but concerns exist on its limited sorption capacity. However, limited quantitative data is available, particularly considering the wide range of contaminants and water quality conditions that occur in stormwater. This study utilized batch tests to investigate the capability of conventional BSM for simultaneous removal of three nutrients (ammonium, nitrate, and phosphate), six metals (Cd, Cr, Cu, Ni, Pb and Zn), and four polycyclic aromatic hydrocarbons (PAHs: naphthalene, acenaphthylene, phenanthrene, and pyrene) from synthetic stormwater. Moreover, the effects of co-contaminants and different stormwater chemistry parameters (pH, salinity, and dissolved organic carbon (DOC)) on BSM sorption capacity were investigated. BSM was not effective for nutrients removal; however, it had good removal efficiency for metals such as Cu, Pb, and Cr which are less soluble at neutral pH values compared to metals such as Ni, Cd and Zn. Moreover, BSM was effective for removing PAHs with higher hydrophobicity such as pyrene and phenanthrene. Metals sorption capacity of BSM was greater at higher pH, lower salinity and DOC; however, the sorption capacity of BSM for PAHs was not sensitive to stormwater chemistry parameters. However, competitive sorption had a notable effect on low molecular weight PAHs, Cd, and Ni. This study provides a quantitative evaluation of the BSM performance and compares the sorption capacity to potential sorptive amendments used in stormwater management. While select sorbent amendments out-performed the BSM, this was not universal and was contaminant specific; careful consideration of water quality enhancement goals and solution chemistry are required in selecting a sorbent. Overall, this study identifies the possible limitations in BSM compositions and factors that may adversely affect BSM sorption capacity, and finally describes options to enhance BSM performance and recommendations for future research.

Seismic Performance Evaluation of Corrosion-Damaged Reinforced Concrete Columns Controlled by Shear Based on Experiment and FEA

It is extremely important to investigate the effect of the seismic performance of corrosion-damaged reinforced concrete (RC) members, in terms of strength and deformability, on the seismic performance of the entire building. This will allow a more accurate assessment of the seismic performance of RC structures with corroded members, including beams and columns. However, current methods of evaluating the seismic performance of RC structures fail to fully consider the influence of reinforcement corrosion and other performance deterioration of RC members. The main objective of this study is to propose a practical method of evaluating the seismic performance of RC structures with corrosion-damaged members, identifying factors contributing to structural performance deterioration based on strength and deformability for direct, quantitative evaluation of seismic performance. To achieve the aforementioned objective, the authors examined the effects of reinforcement corrosion on the structural behavior of RC beams and factors contributing to structural performance deterioration. Past experiments verified the strong correlation between the half-cell potential (HCP) before and after reinforcement corrosion and the reduction factor based on energy absorption capacity. However, current research evaluates the correlation between the extent of corrosion and structural performance deterioration of RC beam members, which are not members that resist lateral force. As such, the results cannot be directly applied to the evaluation of the seismic performance of RC structures containing corrosion-damaged members. To achieve this study’s main purpose of proposing a practical method of evaluating the seismic performance of RC structures comprised of corrosion-damaged members, analytical methods including structural experiments should be applied to corrosion-damaged lateral resisting members, namely, column members of the shear failure type with non-seismic details. This study performed cyclic loading tests on columns of the shear failure type having reinforcement corrosion to examine the correlation between HCP before and after corrosion and seismic performance deterioration. At the same time, finite element analysis (FEA) was carried out in consideration of the weakened bonding between steel and concrete, so as to analyze the correlation between structural performance deterioration before and after corrosion of shear columns. Through a comparison of the experimental findings and FEA results, this study proposed a seismic performance reduction factor in relation to the extent of corrosion of shear columns.

Multi-objective optimization of aquifer storage and recovery operations under uncertainty via machine learning surrogates

Aquifer storage and recovery (ASR) is an important water management approach to store excess surface water into aquifers for later use. Quantitative evaluation of ASR performance is not a trivial task and yet becomes more exacting when uncertainty analysis is added to the dimensionality of the problem. Inclusion of uncertainty into the framework of scheduling optimal ASR operations also increases the level of complexity. This study integrates a surrogate modeling approach coupled with a mixed integer nonlinear programming (MINLP) algorithm to optimize multi-objective ASR operations. The uncertainties are analyzed based upon a thorough sampling of the parameters space as well as a novel analysis of Pareto fronts and variograms of representative solutions. Knee point of representative Pareto fronts is selected for in-depth analysis. As a solution to the dimensionality of the problem, Artificial Neural Network (ANN) is employed to generate surrogate models for predicting groundwater levels and injectate distribution within the aquifer during ASR operations. The computational complexity in building a large number of ANNs and deriving of numerous Pareto fronts via solving the MINLP problem are overcome by the assistance of parallel computing. The results show that optimal ASR operations are highly influenced by hydraulic conductivity and longitudinal dispersivity. Higher hydraulic conductivity values lead to a higher number of active stress periods during storage and recovery phases, which requires large volume of extraction to recover the dispersed injectate. In contrast, higher ratios of longitudinal dispersivity to hydraulic conductivity adversely impact the injectate recovery efficiency. Through meaningful representation of objective function uncertainty by variograms, it is inferred that injectate recovery efficiency is more sensitive to longitudinal dispersivity than hydraulic conductivity.

Vision-based movement recognition reveals badminton player footwork using deep learning and binocular positioning

Coordinating dynamic interceptive actions in sports like badminton requires skilled performance in getting the racket into the right place at the right time. For this reason, the strategic movement and placement of one's feet, or footwork, is an important part of competitive performance. Developing an automated, efficient, and economical method to record individual movement characteristics of players is critical and can benefit athletes and motor control specialists. Here, we propose new methods for recording data on the footwork of individual badminton players, in which deep learning is used to obtain image coordinates (2D) of their shoes and binocular positioning to reconstruct the 3D coordinates of the shoes. Results show that the final positioning accuracy is 74.7%. Using the proposed methods, we revealed inter-individual adaptations in the footwork of several participants during competitive performance. The data provided insights on how individual participants coordinated footwork to intercept the projectile, by varying the distance traveled on court and jump height. Compared with visual observations by biomechanists and motor control specialists, the proposed methods can obtain quantitative data, provide analysis and evaluation of each participant's performance, revealing personal characteristics that could be targeted to shape the individualized training programs of players to refine their badminton footwork.