Currently X-ray images are clinically graded by experienced clinicians using the Kellgren and Lawrence(KL)scoring ***,individual scoring is subjective and error *** study proposes an approach for automated knee osteoa...
详细信息
Currently X-ray images are clinically graded by experienced clinicians using the Kellgren and Lawrence(KL)scoring ***,individual scoring is subjective and error *** study proposes an approach for automated knee osteoarthritis classification based on deep neural *** knee X-ray images are first preprocessed with frequency-domain filtering and histogram normalisation,making the trabecular bone texture more obvious and benefiting the subsequent classification ***,a two-step classification strategy is proposed by extracting the joint centre based on the VGG network and classifying osteoarthritis grades based on the ResNet-50 *** addition,a rebalance operation is proposed to deal with the dataset unbalance problem,and a quick search technique is proposed to improve the iterative search efficiency for the joint *** all of these techniques,a classification accuracy of 81.41%is obtained,which is higher compared to the state-of-the-art approaches.
The main current approaches for generation of the packed bed models are based on rigid body dynamics(RBD)and Newton's laws(discrete element methods-DEM).This paper deals with the development and analysis of a nove...
详细信息
The main current approaches for generation of the packed bed models are based on rigid body dynamics(RBD)and Newton's laws(discrete element methods-DEM).This paper deals with the development and analysis of a novel code based on analytical geometry approach for the packed bed *** architecture and main algorithms of the novel code are described and *** parameters of the packed bed generated via the novel code are compared with experimental data and packed beds generated via Blender(RBD),Yade(DEM).The novel code demonstrates many advantages,such as good correlation with experimental data,no overlaps between pellets in the packed bed,and a low computational time for packed bed *** packed bed model can be directly exported *** *** advantages are also demonstrated and *** novel code is attached to this paper and can be freely used by engineers and scientists.
The automatic assembly of dual peg-in-hole often relies on the concrete CAD model, either explicitly or implicitly. However, especially in daily life, the shapes of pegs vary, and the robot cannot always obtain an acc...
详细信息
ISBN:
(数字)9798350358513
ISBN:
(纸本)9798350358520
The automatic assembly of dual peg-in-hole often relies on the concrete CAD model, either explicitly or implicitly. However, especially in daily life, the shapes of pegs vary, and the robot cannot always obtain an accurate CAD model of the peg before performing the insertion task. Therefore, inspired by the force constraint during contact, we used contact force as the completion indicator of the assembly and proposed a novel two-stage assembly strategy for unknown-shaped dual peg-in-hole. Additionally, a variable remote compliance center method is employed to decouple the contact forces of two pegs and their adjustments. Three types of unidirectional movement modes—exploration, compliance, retention—are utilized to guide the peg to contact with the hole under large initial offsets. The performance of the proposed assembly strategy was evaluated through a series of experiments using various shapes of pegs. The results show that our method effectively completes arbitrary mixed-shaped dual peg-in-hole task under large initial offsets in terms of orientation error (>20°) and position error (>30mm) acorss all test cases.
The soft continuum arm has extensive application in industrial production and human life due to its superior safety and flexibility. Reinforcement learning is a powerful technique for solving soft arm continuous contr...
详细信息
The soft continuum arm has extensive application in industrial production and human life due to its superior safety and flexibility. Reinforcement learning is a powerful technique for solving soft arm continuous control problems, which can learn an effective control policy with an unknown system model. However, it is often affected by the high sample complexity and requires huge amounts of data to train, which limits its effectiveness in soft arm control. An improved policy gradient method, policy gradient integrating long and short-term rewards denoted as PGLS, is proposed in this paper to overcome this issue. The shortterm rewards provide more dynamic-aware exploration directions for policy learning and improve the exploration efficiency of the algorithm. PGLS can be integrated into current policy gradient algorithms, such as deep deterministic policy gradient(DDPG). The overall control framework is realized and demonstrated in a dynamics simulation environment. Simulation results show that this approach can effectively control the soft arm to reach and track the targets. Compared with DDPG and other model-free reinforcement learning algorithms, the proposed PGLS algorithm has a great improvement in convergence speed and performance. In addition, a fluid-driven soft manipulator is designed and fabricated in this paper, which can verify the proposed PGLS algorithm in real experiments in the future.
In the new era of China, with the improvement of people's level day by day, people's awareness of animal protection is gradually enhanced. However, the lack of operator experience of the breeder will cause the...
详细信息
Flexible pressure sensors show significant potential for applications in the fields of intelligent wearable devices,electronic skins,and health ***,the fast response saturation and high viscoelasticity of the flexible...
详细信息
Flexible pressure sensors show significant potential for applications in the fields of intelligent wearable devices,electronic skins,and health ***,the fast response saturation and high viscoelasticity of the flexible sensing materials often result in reduced sensitivity and increased response hysteresis,limiting the practical application of these ***,achieving flexible pressure sensors with both high sensitivity and wide detection range still remains great *** this study,bioinspired by the forcesensitive sensing mechanism and physiological structure of human skin,we propose a low-cost flexible fabrication method for high-performance piezoresistive flexible pressure sensor based on graphene/polydimethylsiloxane(PDMS)composite *** results show that the sensor has an ultra-high sensitivity(321 kPa^(-1)),wide detection range(0.01-1000 kPa),fast response time(29 ms),and exhibits stability over 5000 *** addition,the successful detections and applications indicate the wide application prospect of the developed sensor in fields of health monitoring,human-machine interactions and intelligent robotic perception.
It is a great challenge for reservoir engineers to accurately and quickly model the subsurface flow surrogate for oil and gas reservoirs. The traditional numerical simulation methods are high computational complexity ...
详细信息
ISBN:
(纸本)9781959025375
It is a great challenge for reservoir engineers to accurately and quickly model the subsurface flow surrogate for oil and gas reservoirs. The traditional numerical simulation methods are high computational complexity and time-consuming. The widely used pure data- driven flow surrogate methods require massive high-quality data due to lack of theoretical foundation. Therefore, it is necessary to develop transfer learning methods integrating prior knowledge with data-driven deep learning methods to solve complex seepage problems. To reduce data requirements and improving modeling efficiency, a theory-guided and data-driven transfer learning method is proposed to build the fast and accurate subsurface flow surrogate model. Specifically, a data-driven machine learning method is first proposed to simulate and predict the flow processes and build the primary surrogate model. In addition, physical mechanism and constraints are embedded into the data-driven model to make the prediction results satisfy the prior domain knowledge. The transfer learning method based on physics-guided neural network (TL-PG) integrates the seepage theory with sparse spatial data to improve the prediction accuracy of the surrogate model. The proposed TL-PG method is verified by a subsurface flow problem in heterogeneous reservoir models. First, we build a flow field to simulate 50 years of production history. A physics-guided neural network model is trained based on the samples from the first 30 years and tested based on the last 20 years of data. The relative L2 loss and the coefficient of determination R2 are used for comparison. Compared with the purely data-driven method, the relative L2 loss of physics-guided neural network is increased by 16%, and the mean coefficient of determination R2 is up to 0.8932, which means the embedded physical mechanism can greatly improve the performance of neural networks. Secondly, the physics-guided neural network is selected as the pretraining model. Then, th
In this article, we present a multi-robot continuous ice thickness measurement system that can operate in plateau glacial environments with natural slopes up to 30°, large crevasses of glacier, slippery snow/ice ...
详细信息
Semantic attack, as a covert and highly destructive network attack, seriously threatens the security of automatic guided vehicle (AGV) system. To make it worse, the dynamic change of wireless channel makes semantic at...
详细信息
Optogenetics technology has greatly promoted the development of neuroscience. Flexible gene manipulation tools and sensitive light activation methods have provided convenience for neural function research. However, th...
详细信息
暂无评论