Design Exploration Approach Research Articles

TB-Net: A Tailored, Self-Attention Deep Convolutional Neural Network Design for Detection of Tuberculosis Cases From Chest X-Ray Images.

Tuberculosis (TB) remains a global health problem, and is the leading cause of death from an infectious disease. A crucial step in the treatment of tuberculosis is screening high risk populations and the early detection of the disease, with chest x-ray (CXR) imaging being the most widely-used imaging modality. As such, there has been significant recent interest in artificial intelligence-based TB screening solutions for use in resource-limited scenarios where there is a lack of trained healthcare workers with expertise in CXR interpretation. Motivated by this pressing need and the recent recommendation by the World Health Organization (WHO) for the use of computer-aided diagnosis of TB in place of a human reader, we introduce TB-Net, a self-attention deep convolutional neural network tailored for TB case screening. We used CXR data from a multi-national patient cohort to train and test our models. A machine-driven design exploration approach leveraging generative synthesis was used to build a highly customized deep neural network architecture with attention condensers. We conducted an explainability-driven performance validation process to validate TB-Net's decision-making behavior. Experiments on CXR data from a multi-national patient cohort showed that the proposed TB-Net is able to achieve accuracy/sensitivity/specificity of 99.86/100.0/99.71%. Radiologist validation was conducted on select cases by two board-certified radiologists with over 10 and 19 years of experience, respectively, and showed consistency between radiologist interpretation and critical factors leveraged by TB-Net for TB case detection for the case where radiologists identified anomalies. The proposed TB-Net not only achieves high tuberculosis case detection performance in terms of sensitivity and specificity, but also leverages clinically relevant critical factors in its decision making process. While not a production-ready solution, we hope that the open-source release of TB-Net as part of the COVID-Net initiative will support researchers, clinicians, and citizen data scientists in advancing this field in the fight against this global public health crisis.

COVIDNet-CT: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases From Chest CT Images.

The coronavirus disease 2019 (COVID-19) pandemic continues to have a tremendous impact on patients and healthcare systems around the world. In the fight against this novel disease, there is a pressing need for rapid and effective screening tools to identify patients infected with COVID-19, and to this end CT imaging has been proposed as one of the key screening methods which may be used as a complement to RT-PCR testing, particularly in situations where patients undergo routine CT scans for non-COVID-19 related reasons, patients have worsening respiratory status or developing complications that require expedited care, or patients are suspected to be COVID-19-positive but have negative RT-PCR test results. Early studies on CT-based screening have reported abnormalities in chest CT images which are characteristic of COVID-19 infection, but these abnormalities may be difficult to distinguish from abnormalities caused by other lung conditions. Motivated by this, in this study we introduce COVIDNet-CT, a deep convolutional neural network architecture that is tailored for detection of COVID-19 cases from chest CT images via a machine-driven design exploration approach. Additionally, we introduce COVIDx-CT, a benchmark CT image dataset derived from CT imaging data collected by the China National Center for Bioinformation comprising 104,009 images across 1,489 patient cases. Furthermore, in the interest of reliability and transparency, we leverage an explainability-driven performance validation strategy to investigate the decision-making behavior of COVIDNet-CT, and in doing so ensure that COVIDNet-CT makes predictions based on relevant indicators in CT images. Both COVIDNet-CT and the COVIDx-CT dataset are available to the general public in an open-source and open access manner as part of the COVID-Net initiative. While COVIDNet-CT is not yet a production-ready screening solution, we hope that releasing the model and dataset will encourage researchers, clinicians, and citizen data scientists alike to leverage and build upon them.

Full Factorial Design Exploration Approach for Multi-Objective Optimization on the (FDM) 3D Printed Part

In the manufacturing industry, especially in automotive, quality, precision and productivity on the part that produces is crucial. 3D Printing technology offers a significant advantage to the manufacturer because its ability to produce complex geometry and low-cost investment risk compared with injection moulding. However, there are several issues of using this technology in mass scale and of the issue is dimensional accuracy. In this study, the application of optimisation approach which is Full Factorial Design (FFD) approach which has employed on 3D Printed bottom housing part made from Polylactic Acid (PLA) which were printed using Fused Deposition Modelling (FDM) 3D printer in order to minimise shrinkage on 3D printed parts. Based on the optimisation work, the results showed the performance of FFD approach provides a good dimensional accuracy compared to the drawing specification for the printed part. Therefore, this research provides beneficial scientific knowledge and alternative solution for the additive manufacturing process in industries application to enhance the quality of the 3D printed parts produced using FDM 3D printer machine.

Design exploration of additively manufactured metamaterials

Additive manufacturing (AM) is making a profound impact on our ability to realize complex metamaterials and structures, but fully realizing the manufacturing freedom afforded by AM requires some significant advances in engineering design methods and tools. For some additive manufacturing applications, simulation-based design tools may be required to explore a hierarchy of features, ranging in size from microns to meters. At the same time, these tools need to provide real-time feedback on the constraints and process-structure-property relationships relevant to specific AM technologies, and this Design-for-AM feedback is needed during the design process, rather than at the end. To address these challenges, a design exploration approach has been established for creating inverse maps of promising regions of a hierarchical structural/material design space. The approach utilizes machine learning classifiers for identifying sets of promising solutions to a materials design problem, combined with statistical characterization of geometric features and material properties to ensure that the designs are robustly manufacturable. The capabilities of the approach are demonstrated by applying it to the hierarchical design of negative stiffness metamaterials for energy absorption applicationsAdditive manufacturing (AM) is making a profound impact on our ability to realize complex metamaterials and structures, but fully realizing the manufacturing freedom afforded by AM requires some significant advances in engineering design methods and tools. For some additive manufacturing applications, simulation-based design tools may be required to explore a hierarchy of features, ranging in size from microns to meters. At the same time, these tools need to provide real-time feedback on the constraints and process-structure-property relationships relevant to specific AM technologies, and this Design-for-AM feedback is needed during the design process, rather than at the end. To address these challenges, a design exploration approach has been established for creating inverse maps of promising regions of a hierarchical structural/material design space. The approach utilizes machine learning classifiers for identifying sets of promising solutions to a materials design problem, combined with statistical char...

Exploration of Optimal Powertrain Design Using Realistic Load Profiles

The electrification of bus-based public transportation contributes to the goal of reducing the adverse environmental impacts caused by urban transportation. However, the penetration of electric vehicles has been slow due to their lower vehicle range and total costs in comparison to vehicles driven by internal combustion engines. By improving the powertrain efficiency, the total costs can be reduced for the same vehicle range. Therefore, this paper proposes a holistic design exploration approach to investigate and identify the optimal powertrain concept for electric city buses based on the component costs and energy consumption costs. The load profiles of speed, slope, and passenger occupancy profiles are derived for a selected bus route in Singapore, which is used in a powertrain design exploration for a 30-passenger vehicle. Six different powertrain architectures are analyzed, together with single and multi-speed gearbox configurations, to identify the optimal powertrain architecture and the resulting component sizes. The powertrain configurations are further analyzed in terms of their influence on the vehicle characteristics and total costs. Multi-motor configurations were found to have better vehicle characteristics and lower total costs in comparison to single rear motor configurations. Concepts with motors on the front and a rear axle could shift the load points to a higher efficiency region, resulting in lower energy consumption and energy costs. The optimal powertrain concept was a fixed-speed two-motor configuration, with a booster motor on the front axle and a motor on the rear axle.

Design Exploration of Reliably Manufacturable Materials and Structures With Applications to Negative Stiffness Metamaterials and Microstereolithography1

One of the challenges in designing metamaterials for additive manufacturing (AM) is accounting for the differences between as-designed and as-built geometries and material properties. From a designer's perspective, these differences can lead to degradation of part and metamaterial performance, which is especially difficult to accommodate in small-lot or one-of-a-kind production. In this context, each part is unique, and therefore, extensive iteration is costly. Designers need a means of exploring the design space while simultaneously considering the reliability of additively manufacturing particular candidate designs. In this work, a design exploration approach, based on Bayesian network classifiers (BNC), is extended to incorporate manufacturing variation into the design exploration process and identify designs that reliably meet performance requirements when this variation is taken into account. The example application is the design of negative stiffness (NS) metamaterials, in which small volume fractions of NS inclusions are embedded within a host material. The resulting metamaterial or composite exhibits macroscopic mechanical stiffness and loss properties that exceed those of the base matrix material. The inclusions are fabricated with microstereolithography with features on the scale of tens of microns, but variability is observed in material properties and dimensions from specimen to specimen. This variability is measured and modeled via design, fabrication, and characterization of metrology parts. The quantified manufacturing variability is incorporated into the BNC approach as a manufacturability classifier to identify candidate designs that achieve performance targets reliably, even when manufacturing variability is taken into account.

Multi-objective design exploration approach for Ravenscar real-time systems

This article deals with the design exploration and verification of real-time critical systems. Assigning the functions to the tasks of the target real-time operating system is a part of the design process. Finding a suitable design involves many important design decisions that have a strong impact on the system quality criteria. However, with the increasing complexity and scale of today’s systems and the large number of possible design solutions, making design decisions while balancing conflicting quality criteria becomes error-prone and unmanageable for designers. We propose an automated method using a multi-objective evolutionary algorithm guided by an architectural clustering technique. This method allows designers to search the design space for schedulable solutions with respect to multiple competing performance criteria. To assess our method, several evaluations were performed. One of them shows that we were able to produce the exact optimal solution sets for $$55\%$$ of the studied problem instances.

On the EU approach for DEMO architecture exploration and dealing with uncertainties

One of the difficulties inherent in designing a future fusion reactor is dealing with uncertainty. As the major step between ITER and the commercial exploitation of nuclear fusion energy, DEMO will have to address many challenges – the natures of which are still not fully known. Unlike fission reactors, fusion reactors suffer from the intrinsic complexity of the tokamak (numerous interdependent system parameters) and from the dependence of plasma physics on scale – prohibiting design exploration founded on incremental progression and small-scale experimentation. For DEMO, this means that significant technical uncertainties will exist for some time to come, and a systems engineering design exploration approach must be developed to explore the reactor architecture when faced with these uncertainties. Important uncertainties in the context of fusion reactor design are discussed and a strategy for dealing with these is presented, treating the uncertainty in the first wall loads as an example.

Robust engineering: improved inductive design exploration approach to bionic system

Multidimensional space biomimetic information of space variables is acquired by evaluating bionic degree indices of them. According to bionic degree of each space variable, comprehensive hyperdimensional error margin index in variable space is defined to characterise bionic robustness of discrete points in input space based on inductive design exploration method. Feasible point checking equation is established, which considers differences between space variables, to further reduce target dimensions in optimisation and distinguish variables with different bionic degree. Compromise decision support problem method is used to identify the best solution from the subset using deviation of comprehensive hyperdimensional error margin index in each output space as objective function.

S.H.E.E.P. for Sleeping in Zero-G

What it is like to sleep in zero gravity? Is it ever occurred to you? Sleep is actually a physical and mental resting state in which a person becomes relatively inactive, unaware of the environment, and is partially detachment from the world. It is a challenge for architects to design in a very extreme environment, which has different gravity, radiation exposure to avoid, the absence of basic needs (water, oxygen, etc.), sense of orientation (where is the top and where is the bottom?) etc. The lack of ability for human to stand straight in zero gravity environment – fetal position – leads to the choosing of that position for designing sleeping compartment in space – mimicking a sleeping baby, which is, in fact, the healthiest sleeping position. This idea becomes our guideline in proposing the design of a sleeping compartment in zero gravity, particularly in space station. It gives potential advantage for reducing the payloads of habitat module; size and weight, which is a common problems in space travel; mainly for reducing fuel and cost. But on the other hand, the quality of a good sleep should be considered, which is the main aspect of this design. What is a feasible sleeping compartment design for optimizing those needs? This research uses a design exploration approach to solve the problems and to find a suitable solution. The end result from this activity is S.H.E.E.P; Safe Haven with Ergonomics and Effective Performance. This sleeping compartment design is a private space for crew to rest comfortably without any interference from the external environment. This compartment is also equipped with necessary tools.