Trauma mortality results from a multitude of non-linear dependent risk factors including patient demographics, injury characteristics, medical care provided, and characteristics of medical facilities; yet traditional approach attempted to capture the
se relationships using rigid regression models. We hypothesized that a transfer learning based machine learning algorithm could deeply understand a trauma patients condition and accurately identify individuals at high risk for mortality without relying on restrictive regression model criteria. Anonymous patient visit data were obtained from years 2007-2014 of the National Trauma Data Bank. Patients with incomplete vitals, unknown outcome, or missing demographics data were excluded. All patient visits occurred in U.S. hospitals, and of the 2,007,485 encounters that were retrospectively examined, 8,198 resulted in mortality (0.4%). The machine intelligence model was evaluated on its sensitivity, specificity, positive and negative predictive value, and Matthews Correlation Coefficient. Our model achieved similar performance in age-specific comparison models and generalized well when applied to all ages simultaneously. While testing for confounding factors, we discovered that excluding fall-related injuries boosted performance for adult trauma patients; however, it reduced performance for children. The machine intelligence model described here demonstrates similar performance to contemporary machine intelligence models without requiring restrictive regression model criteria or extensive medical expertise.
Sentiment Analysis and Emotion Detection in conversation is key in several real-world applications, with an increase in modalities available aiding a better understanding of the underlying emotions. Multi-modal Emotion Detection and Sentiment Analysi
s can be particularly useful, as applications will be able to use specific subsets of available modalities, as per the available data. Current systems dealing with Multi-modal functionality fail to leverage and capture - the context of the conversation through all modalities, the dependency between the listener(s) and speaker emotional states, and the relevance and relationship between the available modalities. In this paper, we propose an end to end RNN architecture that attempts to take into account all the mentioned drawbacks. Our proposed model, at the time of writing, out-performs the state of the art on a benchmark dataset on a variety of accuracy and regression metrics.
Bandwidth slicing is introduced to support federated learning in edge computing to assure low communication delay for training traffic. Results reveal that bandwidth slicing significantly improves training efficiency while achieving good learning accuracy.
This paper presents a new conditional GAN (named convex relaxing CGAN or crCGAN) to replicate the conventional constrained topology optimization algorithms in an extremely effective and efficient process. The proposed crCGAN consists of a generator a
nd a discriminator, both of which are deep convolutional neural networks (CNN) and the topology design constraint can be conditionally set to both the generator and discriminator. In order to improve the training efficiency and accuracy due to the dependency between the training images and the condition, a variety of crCGAN formulation are introduced to relax the non-convex design space. These new formulations were evaluated and validated via a series of comprehensive experiments. Moreover, a minibatch discrimination technique was introduced in the crCGAN training process to stabilize the convergence and avoid the mode collapse problems. Additional verifications were conducted using the state-of-the-art MNIST digits and CIFAR-10 images conditioned by class labels. The experimental evaluations clearly reveal that the new objective formulation with the minibatch discrimination training provides not only the accuracy but also the consistency of the designs.
In this study, a novel topology optimization approach based on conditional Wasserstein generative adversarial networks (CWGAN) is developed to replicate the conventional topology optimization algorithms in an extremely computationally inexpensive way
. CWGAN consists of a generator and a discriminator, both of which are deep convolutional neural networks (CNN). The limited samples of data, quasi-optimal planar structures, needed for training purposes are generated using the conventional topology optimization algorithms. With CWGANs, the topology optimization conditions can be set to a required value before generating samples. CWGAN truncates the global design space by introducing an equality constraint by the designer. The results are validated by generating an optimized planar structure using the conventional algorithms with the same settings. A proof of concept is presented which is known to be the first such illustration of fusion of CWGANs and topology optimization.
In this paper we study a role of F-centers, hole centers and excitons in energy transfer in Eu-doped BaBrI crystals. Optical absorption spectra, thermally stimulated (TSL) and photostimulated (PSL) luminescence in wide temperature range 7-300 K are s
tudied in undoped and doped with different concentrations of Eu ions BaBrI crystals. Based on experimental and calculated results two possible energy transfer processes from host to Eu$^{2+}$ ions are established.
Topology design optimization offers tremendous opportunity in design and manufacturing freedoms by designing and producing a part from the ground-up without a meaningful initial design as required by conventional shape design optimization approaches.
Ideally, with adequate problem statements, to formulate and solve the topology design problem using a standard topology optimization process, such as SIMP (Simplified Isotropic Material with Penalization) is possible. In reality, an estimated over thousands of design iterations is often required for just a few design variables, the conventional optimization approach is in general impractical or computationally unachievable for real world applications significantly diluting the development of the topology optimization technology. There is, therefore, a need for a different approach that will be able to optimize the initial design topology effectively and rapidly. Therefore, this work presents a new topology design procedure to generate optimal structures using an integrated Generative Adversarial Networks (GANs) and convolutional neural network architecture.
We report data on the luminescence spectra associated with photochromic centers in X-ray irradiated calcium fluoride crystals doped with Lu ions. Irradiation in low energy photochromic centers absorption band excites emission, which can be identify w
ith transitions into photochromic centers. Ab initio calculation of absorption spectrum of photochromic center agrees rather well with experimental data.
We investigate the scattering and localization properties of edge and bulk states in a disordered two-dimensional topological insulator when they coexist at the same fermi energy. Due to edge-bulk backscattering (which is not prohibited emph{a priori
} by topology or symmetry), Anderson disorder makes the edge and bulk states localized indistinguishably. Two methods are proposed to effectively decouple them and to restore robust transport. The first kind of decouple is from long range disorder, since edge and bulk states are well separated in $k$ space. The second one is from an edge gating, owing to the edge nature of edge states in real space. The latter can be used to electrically tune a system between an Anderson insulator and a topologically robust conductor, i.e., a realization of a topological transistor.
Using standard quantum network method, we analytically investigate the effect of Rashba spin-orbit coupling (RSOC) and a magnetic field on the spin transport properties of a polygonal quantum ring. Using Landauer-Buttiker formula, we have found that
the polarization direction and phase of transmitted electrons can be controlled by both the magnetic field and RSOC. A device to generate a spin-polarized conductance in a polygon with an arbitrary number of sides is discussed. This device would permit precise control of spin and selectively provide spin filtering for either spin up or spin down simply by interchanging the source and drain.
