Image and Feature Space Based Domain Adaptation for Vehicle Detection

The application of deep learning in the field of object detection has experienced much progress. However, due to the domain shift problem, applying an off-the-shelf detector to another domain leads to a significant performance drop. A large number of ground truth labels are required when using another domain to train models, demanding a large amount of human and financial resources. In order to avoid excessive resource requirements and performance drop caused by domain shift, this paper proposes a new domain adaptive approach to cross-domain vehicle detection. Our approach improves the cross-domain vehicle detection model from image space and feature space. We employ objectives of the generative adversarial network and cycle consistency loss for image style transfer in image space. For feature space, we align feature distributions between the source domain and the target domain to improve the detection accuracy. Experiments are carried out using the method with two different datasets, proving that this technique effectively improves the accuracy of vehicle detection in the target domain.     

A Novel Beam Search to Improve Neural Machine Translation for English-Chinese

Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, overcoming the weaknesses of conventional phrase-based translation systems. Although NMT based systems have gained their popularity in commercial translation applications, there is still plenty of room for improvement. Being the most popular search algorithm in NMT, beam search is vital to the translation result. However, traditional beam search can produce duplicate or missing translation due to its target sequence selection strategy. Aiming to alleviate this problem, this paper proposed neural machine translation improvements based on a novel beam search evaluation function. And we use reinforcement learning to train a translation evaluation system to select better candidate words for generating translations. In the experiments, we conducted extensive experiments to evaluate our methods. CASIA corpus and the 1,000,000 pairs of bilingual corpora of NiuTrans are used in our experiments. The experiment results prove that the proposed methods can effectively improve the English to Chinese translation quality.     

Theoretical Prediction of Chiral 3D Hybrid Organic–Inorganic Perovskites

Hybrid organic–inorganic perovskites (HOIPs), in particular 3D HOIPs, have demonstrated remarkable properties, including ultralong charge‐carrier diffusion lengths, high dielectric constants, low trap densities, tunable absorption and emission wavelengths, strong spin–orbit coupling, and large Rashba splitting. These superior properties have generated intensive research interest in HOIPs for high‐performance optoelectronics and spintronics. Here, 3D hybrid organic–inorganic perovskites that implant chirality through introducing the chiral methylammonium cation are demonstrated. Based on structural optimization, phonon spectra, formation energy, and ab initio molecular dynamics simulations, it is found that the chirality of the chiral cations can be successfully transferred to the framework of 3D HOIPs, and the resulting 3D chiral HOIPs are both kinetically and thermodynamically stable. Combining chirality with the impressive optical, electrical, and spintronic properties of 3D perovskites, 3D chiral perovskites is of great interest in the fields of piezoelectricity, pyroelectricity, ferroelectricity, topological quantum engineering, circularly polarized optoelectronics, and spintronics.     

A novel method based on convolutional neural networks for deriving standard 12-lead ECG from serial 3-lead ECG

Frontiers of Information Technology & Electronic Engineering - Reconstruction of a 12-lead electrocardiogram (ECG) from a serial 3-lead ECG has been researched in the past to satisfy the need...     

Structural,morphological, dielectric and magnetic properties of Zn-Zr co-doping yttrium iron garnet

In this study, yttrium iron garnet co-doped with Zn and Zr atoms with a chemical formula Y₃Zn_xZr_xFe_(5−2x)O₁₂ (x = 0.0-0.3) has been successfully prepared by the solid-state reaction method. The effects of doping concentration on the microstructure, crystal structure, magnetic properties, and dielectric properties of Y₃Zn_xZr_xFe_(5−2x)O₁₂ were investigated. The microstructure analysis indicates that co-doping of YIG with Zn and Zr can effectively reduce the grain size of the ceramic. The crystal structure results reveal that the doping concentration of Zn–Zr has substantial influence on the lattice parameters of YIG, such as, increases the lattice constant, crystal cell size, and interplanar spacing. However, the second phase of ZrO₂ appears once x ≥ 0.15. Additionally, the dielectric properties of YIG ferrite can be regulated using this Zn–Zr co-doping method. Zn–Zr co-doping can improve the dielectric stability and reduce the dielectric loss at high temperature. The magnetization measurement shows that the saturation magnetization is stabilized at x < 0.15, and the magnetic loss is decreased with the increase in the doping concentration. Overall, the findings show that the ceramic with x = 0.1 exhibits better properties included high saturation magnetization (24.607 emu/g), low magnetic loss (0.0025 @ 1 MHz), and relatively low dielectric loss (496 @ 400°C).