检索结果-内蒙古大学图书馆

Lower limb motor function assessment based on TensorFlow convolutional neural network and kernel entropy component analysis-local tangent space alignment

引用

ADVANCES IN MECHANICAL ENGINEERING 2020年第7期12卷

作者： Zhang, Yan Li, SiNing Zhou, Ying Liu, Jian Hebei Univ Technol Sch Artificial Intelligence Tianjin 300310 Peoples R China Hebei Univ Technol Engn Res Ctr Intelligent Rehabil Minist Educ Tianjin Peoples R China Hebei Univ Technol Hebei Key Lab Robot Sensing & Human Robot Interac Tianjin Peoples R China

Motor function assessment of patients and the elderly is crucial to gait assessment and gait rehabilitation. Accuracy of the assessment is affected by clinician's experience. To solve the problem, this article proposes motor function assessment index to assess the motor function of patients. VICON system collects video of subjects when they are walking. And the original gait videos are pre-processed by the pixel-based adaptive segmenter and extracted by the convolutional neural network. The kernel entropy component analysis and local tangent space alignment reduced the dimensions of extracted features, and motor function assessment index is obtained. The Pearson correlation analysis shows that the motor function assessment index and modified gait abnormality rating scale are significantly correlated, and Pearson correlation coefficient is 0.92. These effectiveness results demonstrate that the proposed method has the considerable potential to promote the future design of automatic motor function assessment for clinical rehabilitation research.

关键词： Convolutional neural network lower limb motor function assessment transfer learning kernel entropy component analysis local tangent space alignment

来源：评论

学校读者我要写书评

暂无评论

Enhanced Probabilistic Inference Algorithm Using Probabilistic Neural Networks for Learning Control

引用

IEEE ACCESS 2019年 7卷 184457-184467页

作者： Li, Yang Guo, Shijie Zhu, Lishuang Mukai, Toshiharu Gan, Zhongxue Hebei Univ Technol State Key Lab Reliabil & Intelligence Elect Equip Tianjin 300130 Peoples R China Hebei Univ Technol Hebei Key Lab Robot Percept & Human Robot Interac Tianjin 300130 Peoples R China Meijyo Univ Fac Informat Sci Nagoya Aichi 2310002 Japan Fudan Univ Inst AI & Robot Shanghai 200433 Peoples R China

In model-based methods of reinforcement learning (RL), the probabilistic inference for learning control (PILCO) algorithm, which relies on Gaussian process (GP) for building probabilistic dynamics models, is getting attention for its advantages of requiring only a small amount of data, and being able to learn from scratch in a few trials by explicitly incorporating model uncertainty into long-term planning. However, the time complexity of the GP, which is cubic with respect to the number of trials, makes it challenging to scale the framework to high-dimensional observation spaces. Moreover, the cost function of a task is limited as a locally quadratic function for calculating the policy gradient analytically. To solve these problems, we proposed a probabilistic neural network (PNN) to replace the GP in building probabilistic dynamics models and develop a deterministic control policy by using long-term predictions. In particular, we determine model uncertainty through basic prior knowledge and calculate cumulative cost by sampling from state distributions. This approach can help reduce the influence of model error and time consumption. Compared with the state-of-the-art model-based RL, the proposed approach can reconcile data efficiency and speed of learning even in high-dimensional observation spaces.

关键词： Reinforcement learning control policy probabilistic dynamics model probabilistic neural network

来源：评论

学校读者我要写书评

暂无评论

A traveling-wave ultrasonic motor utilizing a ring-shaped alumina/PZT vibrator

引用

SMART MATERIALS AND STRUCTURES 2019年第12期28卷 125017-125017页

作者： Wu, Jiang Mizuno, Yosuke Nakamura, Kentaro Hebei Univ Technol State Key Lab Reliabil & Intelligence Elect Equip Tianjin 300130 Peoples R China Hebei Univ Technol Hebei Key Lab Robot Percept & Human Robot Interac Tianjin 300130 Peoples R China Tokyo Inst Technol Lab Future Interdisciplinary Res Sci & Technol Yokohama Kanagawa 2268503 Japan

Considering that high Young?s moduli and low ultrasonic attenuation of fine ceramics may enhance driving force and reduce energy dissipation, in this study, we exploit the usage of fine ceramics as vibrating bodies of ultrasonic motors. Several alumina vibrating bodies were fabricated and bonded to annular lead-zirconate-titanate (PZT) disks to form ring-shaped vibrators, where traveling waves with the 3rd bending modes were excited to frictionally drive the rotor. First, we explored the fundamental vibration properties. As predicted, the alumina/PZT vibrators provided relatively high force factors, high electromechanical coupling factors, and low damping compared to the stainless-steel/PZT one with similar structure. Subsequently, through experimental assessment on load characteristics, we found that the rotation speed of the alumina/PZT motor at 20 V was larger than that of the stainless-steel/PZT motor at 250 V, and meanwhile, it exhibited superior maximal-torque-to-voltage and maximal-output-power-to-voltage ratios;these results imply that satisfactory performance is achievable with our motor. Besides, alumina?s chemical resistance and electrical resistance make our motor potentially applicable to the acid/alkaline atmosphere and the intensively alternating-current magnetic field.

关键词： ultrasonic motors alumina high young?s modulus low ultrasonic attenuation

来源：评论

学校读者我要写书评

暂无评论

A Microfluidic Concentration Gradient Maker with Tunable Concentration Profiles by Changing Feed Flow Rate Ratios

引用

MICROMACHINES 2020年第3期11卷 284-284页

作者： Zhang, Tao Meng, Jiyu Li, Shanshan Yu, Chengzhuang Li, Junwei Wei, Chunyang Dai, Shijie Hebei Univ Technol Hebei Key Lab Robot Sensing & Human Robot Interac Sch Mech Engn Tianjin 300132 Peoples R China Hebei Univ Technol Natl Key Lab Reliabil & Elect Equipment Tianjin 300130 Peoples R China Hebei Univ Technol Dept Comp Sci & Elect Engn Langfang 065000 Peoples R China Hebei Univ Technol Inst Biophys Sch Sci Tianjin 300401 Peoples R China

Microfluidic chips-in which chemical or biological fluid samples are mixed into linear or nonlinear concentration distribution profiles-have generated enormous enthusiasm of their ability to develop patterns for drug release and their potential toxicology applications. These microfluidic devices have untapped potential for varying concentration patterns by the use of one single device or by easy-to-operate procedures. To address this challenge, we developed a soft-lithography-fabricated microfluidic platform that enabled one single device to be used as a concentration maker, which could generate linear, bell-type, or even S-type concentration profiles by tuning the feed flow rate ratios of each independent inlet. Here, we present an FFRR (feed flow rate ratio) adjustment approach to generate tens of types of concentration gradient profiles with one single device. To demonstrate the advantages of this approach, we used a Christmas-tree-like microfluidic chip as the demo. Its performance was analyzed using numerical simulation models and experimental investigations, and it showed an excellent time response (similar to 10 s). With on-demand flow rate ratios, the FFRR microfluidic device could be used for many lab-on-a-chip applications where flexible concentration profiles are required for analysis.

关键词： microfluidics concentration gradient nonlinear feed flow rate ratios mixing

来源：评论

学校读者我要写书评

暂无评论

Tunable microfluidic standing air bubbles and its application in acoustic microstreaming

引用

BIOMICROFLUIDICS 2019年第3期13卷 034114-034114页

作者： Liu, Jixiao Li, Bowen Zhu, Tong Zhou, Yidi Li, Shanshan Guo, Shijie Li, Tiejun Hebei Univ Technol Sch Mech Engn Tianjin 300132 Peoples R China Hebei Univ Technol Hebei Key Lab Smart Sensing & Human Robot Interac Tianjin 300132 Peoples R China Hebei Univ Technol State Key Lab Reliabil & Intelligence Elect Equip Tianjin 300132 Peoples R China

Microbubbles are often used in chemistry, biophysics, and medicine. Properly controlled microbubbles have been proved beneficial for various applications by previous scientific endeavors. However, there is still a plenty of room for further development of efficient microbubble handling methods. Here, this paper introduces a tunable, stable, and robust microbubble interface handling mechanism, named as microfluidic standing air bubbles (mu SABs), by studying the multiphysical phenomena behind the gas-liquid interface formation and variation. A basic mu SAB system consists specially structured fluidic channels, pneumatic channels, and selectively permeable porous barriers between them. The mu SABs originate inside the crevice structures on the fluidic channel walls in a repeatable and robust manner. The volumetric variation of the mu SAB is a multiphysical phenomenon that dominated by the air diffusion between the pneumatic channel and the bubble. Theoretical analysis and experimental data illustrate the coupling processes of the repeatable and linear mu SAB volumetric variation when operated under common handling conditions (control pneumatic pressure: -90kPa to 200kPa). Furthermore, an adjustable acoustic microstreaming is demonstrated as an application using the alterable mu SAB gas-liquid interface. Derived equations and microscopic observations elucidate the mechanism of the continuous and linear regulation of the acoustic microstreaming using varying mu SAB gas-liquid interfaces. The mu SAB system provides a new tool to handle the flexible and controllable gas-liquid interfaces in a repeatable and robust manner, which makes it a promising candidate for innovative biochemical, biophysical, and medical applications.

关键词： Gas liquid interfaces Cavitation bubbles Bubble dynamics Microfluidic devices Microchannel Acoustic streaming Fluid bubbles Mass diffusion Acoustofluidics

来源：评论

学校读者我要写书评

暂无评论

Method of bed exit intention based on the internal pressure features in array air spring mattress

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-15页

作者： Meng, Fanchao Liu, Teng Meng, Chuizhou Zhang, Jianjun Zhang, Yifan Guo, Shijie Hebei Univ Technol Engn Res Ctr Minist Educ Intelligent Rehabil Equipment & Detec Tianjin 300130 Peoples R China Hebei Univ Technol Hebei Key Lab Smart Sensing & Human Robot Integra Tianjin 300130 Peoples R China Hebei Univ Technol Sch Mech Engn Tianjin 300130 Peoples R China Civil Aviat Univ China Sch Comp Sci & Technol Tianjin 300300 Peoples R China

With the population ages, many patients are unable to receive comprehensive care, leading to an increase in hazardous incidents, particularly falls occurring after getting out of bed. To address this issue, this paper proposes a method for recognizing bed-exit intentions using an array air spring mattress. The method integrates convolutional neural networks with feature point matching techniques to identify both global and local features of the array air spring. For global features, a one-dimensional focal loss convolutional neural network (1D-FLCNN) model is employed to classify eight internal pressure time series and determine bed-exit status based on global features. For local features, the distribution matrix and feature point matrix of the internal pressure features are extracted to represent the spatial distribution of bed-exit postures. Euclidean distance is utilized to measure the similarity between these matrices and match bed-exit postures. Finally, the recognition results from both feature types are combined using a logical OR operation to produce the final result. Experimental validation confirms that the proposed method greatly improves the anti-interference capability and effectively avoids the problem of non-recognition due to body position and external environment.

关键词： Bed-exit intention Array air spring mattress Global features Local features Internal pressure

来源：评论

学校读者我要写书评

暂无评论

MOF-derived nitrogen-doped carbon-based trimetallic bifunctional catalysts for rechargeable zinc-air batteries

引用

NANOTECHNOLOGY 2022年第40期33卷 405403-405403页

作者： Zhu, Bo Li, Jing Hou, Zhanrui Meng, Chuizhou Liu, Guihua Du, Xiaohang Guan, Yuming Hebei Univ Technol Sch Mech Engn Hebei Key Lab Smart Sensing & Human Robot Interac State Key Lab Reliabil & Intelligence Elect Equip Tianjin 300130 Peoples R China Hebei Univ Technol Sch Chem Engn & Technol Tianjin Key Lab Chem Proc Safety Tianjin 300130 Peoples R China

Zinc-air battery (ZAB) is a promising new metal-air energy system, but the large overpotentials of oxygen evolution reaction (OER) and oxygen reduction reaction (ORR) around the air electrode lead to their poor energy efficiency. Herein, a novel bifunctional oxygen electrocatalyst is reported with the preparation of a zeolite imidazolate framework (ZIF-67) derived trimetallic composites decorated nitrogen-doped carbon, which consist of NiFe alloy and Co nanoparticles. The ZIF-derived porous N-doped carbon shell can speed up the mass transfer efficiency. Whereas the electronic effect between the formed NiFe alloy and Co nanoparticles, as well as the N-doped carbon framework can enrich the active centers and enhance the electrical conductivity. As a result, the NiFe-Co@NC-450 catalyst shows superior performance manifested as a small potential gap (Delta E = 0.857 V) between the overpotential at 10 mA cm(-2) (E (j=10)) for OER (460 mV) and half-wave potential (E (1/2)) for ORR (0.833 V). The liquid ZABs exhibit a high specific capacity reaching 798 mAh/g(Zn) and a stable cycling performance at 10 mA cm(-2) for more than 200 h. Meanwhile, the NiFe-Co@NC-450 based flexible ZABs also presents robust flexibility and stability. This study has certain implications for the development of economical, powerful and stable bifunctional catalysts for ZABs.

关键词： rechargeable zinc-air batteries bifunctional oxygen electrocatalysts oxygen reduction reaction oxygen evolution reaction trimetallic electrocatalyst

来源：评论

学校读者我要写书评

暂无评论

Pencil-on-Paper Humidity Sensor Treated with NaCl Solution for Health Monitoring and Skin Characterization

引用

NANO LETTERS 2022年第4期23卷 1252-1260页

作者： Niu, Guangyu Wang, Zihan Xue, Ye Chen, Xue Liu, Chaosai Guo, Langang Zhou, Peng Cheng, Huanyu Yang, Li Yan, Jiayi Dutta, Ankan Wang, Ya Du, Shuaijie Hebei Univ Technol Dept Architecture & Art Tianjin 300130 Peoples R China Hebei Univ Technol Sch Mech Engn State Key Lab Reliabil & Intelligence Elect Equipm Hebei Key Lab Smart Sensing & Human Robot Interact Tianjin 300401 Peoples R China Hebei Univ Technol Sch Hlth Sci & Biomed Engn State Key Lab Reliabil & Intelligence Elect Equipm Tianjin 300130 Peoples R China Penn State Univ Dept Engn Sci & Mech University Pk PA 16802 USA Tianjin Tianzhong Yimai Technol Dev Co Ltd Tianjin 300384 Peoples R China

Although flexible humidity sensors are essential for human health monitoring, it is still challenging to achieve high sensitivity and easy disposal with simple, low-cost fabrication processes. This study presents the design and fabrication of highly reliable hand-drawn interdigital electrodes from pencil-on-paper treated with NaCl solution for highly sensitive hydration sensors working over a wide range of relative humidity (RH) levels from 5.6% to 90%. The applications of the resulting flexible humidity sensor go beyond the monitoring of respiratory rate and proximity to characterizations of human skin types and evaluations of skin barrier functions through insensible sweat measurements. The sensor array can also be integrated with a diaper to result in smart diapers to alert for an early diaper change. The design and fabrication strategies presented in this work could also be leveraged for the development of wearable, self-powered, and recyclable sensors and actuators in the future.

关键词： flexible humidity sensors and sensing systems pencil-on-paper characterizations of skin types and barrier functions monitoring of sensible and insensible sweat rate

来源：评论

学校读者我要写书评

暂无评论

Sensitivity Analysis and Interval Multi Objective Optimization for an Occupant Restraint System Considering Craniocerebral Injury

引用

JOURNAL OF MECHANICAL DESIGN 2020年第2期142卷 p1-11页

作者： Liu, Qiming Wu, Xingfu Han, Xu Liu, Jie Zhang, Zheyi Guo, Shijie Hebei Univ Technol Sch Elect Engn State Key Lab Reliabil & Intelligence Elect Equip Tianjin 300401 Peoples R China Hunan Univ Coll Mech & Vehicle Engn State Key Lab Adv Design & Mfg Vehicle Body Changsha 410082 Peoples R China Hebei Univ Technol Sch Mech Engn State Key Lab Reliabil & Intelligence Elect Equip Hebei Key Lab Robot Sensing & Human Robot Interac Tianjin 300401 Peoples R China

In vehicle collision accidents, an occupant restraint system (ORS) is crucial to protect the human body from injury, and it commonly involves a large number of design parameters. However, it is very difficult to quantify the importance of design parameters and determine them in the ORS design process. Therefore, an approach of the combination of the proposed approximate sensitivity analysis (SA) method and the interval multi-objective optimization design is presented to reduce craniocerebral injury and improve ORS protection performance. First, to simulate the vehicle collision process and obtain the craniocerebral injury responses, the integrated finite element model of vehicle -occupant (IFEM-VO) is established by integrating the vehicle, dummy, seatbelt, airbag, etc. Then, the proposed approximate SA method is used to quantify the importance ranking of design parameters and ignore the effects of some nonessential parameters. In the SA process, the Kriging meta model characterizing the relationships between design parameters and injury responses is fitted to overcome the time-consuming disadvantage of IFEM-VO. Finally, according to the results of SA, considering the influence of uncertainty, an interval multiobjective optimization design is implemented by treating the brain injury criteria (BRIC, BrIC) as the objectives and regarding the head injury criterion (HIC) and the rotational injury criterion (RIC) as the constraints. Comparison of the results before and after optimization indicates that the maximum values of the translational and rotational accelerations are greatly reduced, and the ORS protection performance is significantly improved. This study provides an effective way to improve the protection performance of vehicle ORS under uncertainty.

关键词： occupant restraint system craniocerebral injury sensitivity analysis interval multi-objective optimization design Kriging metamodel Monte Carlo method uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Tailorable Capacitive Tactile Sensor Based on Stretchable and Dissolvable Porous Silver Nanowire/Polyvinyl Alcohol Nanocomposite Hydrogel for Wearable human Motion Detection

引用

ADVANCED MATERIALS INTERFACES 2021年第20期8卷

作者： Wang, Peng Li, Guoxian Liu, Jun Hou, Zhanrui Meng, Chuizhou Guo, Shijie Liu, Changhong Fan, Shoushan Hebei Univ Technol Sch Mech Engn Hebei Key Lab Smart Sensing & Human Robot Interac State Key Lab Reliabil & Intelligence Elect Equip Tianjin 300401 Peoples R China Tsinghua Univ Dept Phys Tsinghua Foxconn Nanotechnol Res Ctr Beijing 100084 Peoples R China

Recently, advanced flexible tactile sensors have been widely studied for human motion detection, which is an essential part of human healthcare monitoring. New types of materials with novel composition and structures play a significant role in sensing performance improvement. Herein, a stretchable and dissolvable porous silver nanowire (Ag NW)/polyvinyl alcohol (PVA) nanocomposite hydrogel is fabricated through a facile foaming and freezing-thawing combined approach. The PVA gel is foamed with lots of tailorable micropores to achieve much enhanced stretchability and compressibility. Ag NWs are uniformly embedded inside PVA matrix to increase the permittivity upon introduction of numerous microcapacitors. Incorporated with carbon nanotube network electrodes, a capacitive tactile sensor is developed with high sensitivity (1.9 kPa(-1)), wide detection range (250 kPa), quick response time (25 ms), and remarkable stability over 10 000 loading/unloading cycles. Wearable sensing demonstration of detecting various human motions is performed. The hydrogel-based sensor can be dissolved in hot water within minutes with recycling use of electrode material, which is environmentally friendly. A large-area integrated sensor sheet can be made upon one fabrication process followed by cut into small sensor devices with desired shapes, indicating potential customized mass production. The proposed microporous nanocomposite hydrogel-based sensor is promising in wearable sensing applications.

关键词： hydrogel-based sensors nanocomposite dielectrics polyvinyl alcohol hydrogels silver nanowires stretchable sensors tactile sensors

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：