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.     

Physicochemical characteristics,antioxidant capacity and thermodynamic properties of purple-fleshed potatos dried by radio frequency energy

Abstract

The impacts of using radio frequency (RF) energy to dry purple-fleshed potatoes were investigated and compared to infrared radiation (IR) and microwave (MW) drying techniques. The gelatinization rate, color, flavor, morphological, and structural characteristics, thermodynamic properties, as well as antioxidant capacity were examined. The results indicated that the drying time of RF (70?min) and MW (21?min) were shorter than IR (105?min). The gelatinization ratio of MW, RF, and IR were 94.4?±?2.0, 88.3?±?1.4, and 64.5?±?1.1%, respectively. The degree of crystallization of purple-fleshed potato powder decreased with all three drying methods. RF-dried potatoes were able to retain higher polyphenols (loss rate: 4.3%), total anthocyanin (3.7%), and total flavonoid content (35.1%), whereas IR showed the lowest retention. The content of polyphenols also decreased significantly. Furthermore, after RF heating, the scavenging of free radicals was higher compared to MW and IR.     

Personalized broad learning system for facial expression

Multimedia Tools and Applications - Understanding human emotions through facial expressions is key enabling technology for interactive robots. Most approaches of facial expression recognition are...     

An image encryption scheme based on precision limited chaotic system

Multimedia Tools and Applications - In recent years, various chaotic maps have been used for image encryption. However, most of these image encryption algorithms entail a lot of floating-point...     

铸态Ti-20Zr-20Al钛合金动态压缩力学性能与断裂机制研究

采用X射线衍射仪、金相显微镜、分离式霍普金森杆和扫描电镜等手段研究了Ti-20Zr-20Al钛合金在动态压缩条件下的微观结构、力学性能和断裂机制。结果表明,Ti-20Zr-20Al铸态合金由Zr基体相和TiAl/Ti₃Al针状相组成; 随着应变率增加,合金的抗压强度增加,失效应变显著增加; Ti-20Zr-20Al合金的断裂机制为解理断裂; 随着应变率增加,试验压缩断裂后碎片总数增大,平均粒径减小。采用DID模型模拟的材料碎片尺度与实验结果比较吻合,Grady模型与实验结果的偏差较大。     

D-limonene Inhibits Pentylenetetrazole-Induced Seizure via Adenosine A2A Receptor Modulation on GABAergic Neuronal Activity

Background: Epilepsy is a chronic neurological disorder characterized by the recurrence of seizures. One-third of patients with epilepsy may not respond to antiseizure drugs. Purpose: We aimed to examine whether D-limonene, a cyclic monoterpene, exhibited any antiseizure activity in the pentylenetetrazole (PTZ)-induced kindling mouse model and in vitro. Methods: PTZ kindling mouse model was established by administering PTZ (30 mg/kg) intraperitoneally to mice once every 48 h. We performed immunoblot blots, immunohistochemistry (IHC), and high-performance liquid chromatography (HPLC) analysis after the behavioral study. Results: An acute injection of PTZ (60 mg/kg) induced seizure in mice, while pretreatment with D-limonene inhibited PTZ-induced seizure. Repeated administration of PTZ (30 mg/kg) increased the seizure score gradually in mice, which was reduced in D-limonene (10 mg/kg)-pretreated group. In addition, D-limonene treatment increased glutamate decarboxylase-67 (GAD-67) expression in the hippocampus. Axonal sprouting of hippocampal neurons after kindling was inhibited by D-limonene pretreatment. Moreover, D-limonene reduced the expression levels of Neuronal PAS Domain Protein 4 (Npas4)-induced by PTZ. Furthermore, the adenosine A2A antagonist {"type":"entrez-protein","attrs":{"text":"SCH58261","term_id":"1052882304","term_text":"SCH58261"}}SCH58261 and ZM241385 inhibited anticonvulsant activity and gamma-aminobutyric acid (GABA)ergic neurotransmission-induced by D-limonene. Conclusion: These results suggest that D-limonene exhibits anticonvulsant activity through modulation of adenosine A2A receptors on GABAergic neuronal function.     

A distributed energy system integrating SOFC-MGT with mid-and-low temperature solar thermochemical hydrogen fuel production

Solar thermochemical hydrogen production with energy level upgraded from solar thermal to chemical energy shows great potential. By integrating mid-and-low temperature solar thermochemistry and solid oxide fuel cells, in this paper, a new distributed energy system combining power, cooling, and heating is proposed and analyzed from thermodynamic, energy and exergy viewpoints. Different from the high temperature solar thermochemistry (above 1073.15 K), the mid-and-low temperature solar thermochemistry utilizes concentrated solar thermal (473.15–573.15 K) to drive methanol decomposition reaction, reducing irreversible heat collection loss. The produced hydrogen-rich fuel is converted into power through solid oxide fuel cells and micro gas turbines successively, realizing the cascaded utilization of fuel and solar energy. Numerical simulation is conducted to investigate the system thermodynamic performances under design and off-design conditions. Promising results reveal that solar-to-hydrogen and net solar-to-electricity efficiencies reach 66.26% and 40.93%, respectively. With the solar thermochemical conversion and hydrogen-rich fuel cascade utilization, the system exergy and overall energy efficiencies reach 59.76% and 80.74%, respectively. This research may provide a pathway for efficient hydrogen-rich fuel production and power generation.     

基于Q-learning的不确定环境BDI Agent最优策略规划研究

BDI模型能够很好地解决在特定环境下的Agent的推理和决策问题,但在动态和不确定环境下缺少决策和学习的能力。强化学习解决了Agent在未知环境下的决策问题,却缺少BDI模型中的规则描述和逻辑推理。针对BDI在未知和动态环境下的策略规划问题,提出基于强化学习Q-learning算法来实现BDI Agent学习和规划的方法,并针对BDI的实现模型ASL的决策机制做出了改进,最后在ASL的仿真平台Jason上建立了迷宫的仿真,仿真实验表明,在加入Q-learning学习机制后的新的ASL系统中,Agent在不确定环境下依然可以完成任务。