检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Islam, Mobarakol Vaidyanathan, N. Rajiv Jose, V. Jeya Maria Ren, Hongliang National University of Singapore Singapore Dept. of Biomedical Engineering National University of Singapore Singapore Dept. of Mechanical Engineering NIT Tiruchirappalli India Dept. of Instrumentation and Control Engineering NIT Tiruchirappalli India

Ischemic stroke occurs through a blockage of clogged blood vessels supplying blood to the brain. Segmentation of the stroke lesion is vital to improve diagnosis, outcome assessment and treatment planning. In this work, we propose a segmentation model with adversarial learning for ischemic lesion segmentation. We adopt U-Net with skip connection and dropout as segmentation baseline network and a fully connected network (FCN) as discriminator network. Discriminator network consists of 5 convolution layers followed by leaky-ReLU and an upsampling layer to rescale the output to the size of the input map. Training a segmentation network along with an adversarial network can detect and correct higher order inconsistencies between the segmentation maps produced by ground-truth and the Segmentor. We exploit three modalities (CT, DPWI, CBF) of acute computed tomography (CT) perfusion data provided in ISLES 2018 (Ischemic Stroke Lesion Segmentation) for ischemic lesion segmentation. Our model has achieved dice accuracy of 42.10% with the cross-validation of training and 39% with the testing data. Copyright © 2022, The Authors. All rights reserved.

关键词： Discriminators

来源：评论

学校读者我要写书评

暂无评论

Paced-Curriculum Distillation with Prediction and Label Uncertainty for Image Segmentation

arXiv

引用

arXiv 2023年

作者： Islam, Mobarakol Seenivasan, Lalithkumar Sharan, S.P. Viekash, V.K. Gupta, Bhavesh Glocker, Ben Ren, Hongliang Dept. of Computing Imperial College London United Kingdom Dept. of Biomedical Engineering National University of Singapore Singapore Dept. of Electronics and Communication Engineering National Institute of Technology Tiruchirappalli India Dept. of Instrumentation and Control Engineering National Institute of Technology Tiruchirappalli India Dept. of Mechanical Engineering Indian Institute of Technology Delhi India Dept. of Electrical Engineering Shun Hing Institute of Advanced Engineering The Chinese University of Hong Kong Hong Kong

Purpose: In curriculum learning, the idea is to train on easier samples first and gradually increase the difficulty, while in self-paced learning, a pacing function defines the speed to adapt the training progress. While both methods heavily rely on the ability to score the difficulty of data samples, an optimal scoring function is still under exploration. Methodology: Distillation is a knowledge transfer approach where a teacher network guides a student network by feeding a sequence of random samples. We argue that guiding student networks with an efficient curriculum strategy can improve model generalization and robustness. For this purpose, we design an uncertainty-based paced curriculum learning in self-distillation for medical image segmentation. We fuse the prediction uncertainty and annotation boundary uncertainty to develop a novel paced-curriculum distillation (PCD). We utilize the teacher model to obtain prediction uncertainty and spatially varying label smoothing with Gaussian kernel to generate segmentation boundary uncertainty from the annotation. We also investigate the robustness of our method by applying various types and severity of image perturbation and corruption. Results: The proposed technique is validated on two medical datasets of breast ultrasound image segmentation and robotassisted surgical scene segmentation and achieved significantly better performance in terms of segmentation and robustness. Conclusion: P-CD improves the performance and obtains better generalization and robustness over the dataset shift. While curriculum learning requires extensive tuning of hyper-parameters for pacing function, the level of performance improvement suppresses this limitation. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Analysis of PSO-PID controller for CSTR temperature control 1

Analysis of PSO-PID controller for CSTR temperature control

引用

1st IEEE International Conference on Smart Technologies for Power, Energy and control, STPEC 2020

作者： Deulkar, Pratyush Hanwate, Sandeep College of Engineering Pune Dept. of Instrumentation and Control Pune India

ISBN: (纸本)9781728188737

Continuous Stirred Tank Reactor (CSTR) is a pivotal unit in chemical process industries, and finds many applications. However, it is unstable, nonlinear and disturbance prone. Thus, it needs to be robustly controlled. Industrial process control techniques have greatly progressed over recent decades and numerous control methods have been proposed. Here, we have analyzed a Particle Swarm optimization (PSO) based PID, whose gains are optimized for stabilizing temperature control in CSTR plant. This is carried out by selecting parameters to obtain best possible solution for different conditions. Two input disturbances are considered to ensure and verify that the PSO-PID is able to control the plant robustly. Further, the system response is compared against conventional methods such as Ziegler-Nichols tuning, genetic algorithm and classical PSO. It is found that the patterns of PSO-PID gains versus iterations, are able to improve performance much better against the considered counterparts. © 2020 IEEE.

关键词： Temperature control

来源：评论

学校读者我要写书评

暂无评论

Non invasive assessment of Tissue oxygen using spectroscopy 11

Non invasive assessment of Tissue oxygen using spectroscopy

引用

11th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2020

作者： Shedbale, Priyanka Ashok Mudhalwadkar, R.P. Mandavkar, Saheli College of Engineering Pune Dept. of Instrumentation and Control Pune India

ISBN: (纸本)9781728168517

This paper is about designing and developing an optical system using near infrared spectroscopy to measure the oxygen level in tissues. This oxygen saturation is determined by the value 'Tissue oxygenation index (TOI). This paper aims at finding the TOI values and states if it's in the normal or abnormal ranges. Abnormal ranges can denote problems such as ischemia. Conventionally, pulse oximeter is used to measure saturation in arterial blood. But it cannot detect the concentration of oxygen in tissues. Therefore a point of care system is developed to non-invasively monitor oxygen in tissues of forearm and palm by reflectance oximetry. Temporary occlusion is created by sphygmomanometer for testing and real time data are obtained by Arduino into MATLAB which is used for further signal processing. © 2020 IEEE.

关键词： Tissue

来源：评论

学校读者我要写书评

暂无评论

Biomass Fuel Classification from Agricultural Residues Using Machine Learning

Biomass Fuel Classification from Agricultural Residues Using...

引用

IEEE Region 10 Humanitarian Technology Conference (R10-HTC)

作者： Nikhil Pachauri Himanshu Gupta Om Prakash Verma Sushil Kumar Singh Deepak Verma Ravikumar RN Department of Mechatronics Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Department of Instrumentation and Control Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal Karnataka India Department of Instrumentation and Control Engineering Dr B R Ambedkar National Institute of Technology Jalandhar Jalandhar India Department of Computer Engineering of Computer Engineering Marwadi University Rajkot Gujarat India Dept. of Computer Engineering Marwadi University Rajkot Gujarat India

ISBN: (数字)9798350340204

ISBN: (纸本)9798350340211

This work incorporates an adaptive learning-based boosting (ADboost) ML classifier to classify four types of fuel: agricultural residue, coals, wood, and produced biomass. Further, the ADboost’s hyperparameters, such as learning rate, maximum number of splits, and minimum leaf size are adjusted using teaching learning-based optimization (TLBO), resulting in TADboost. The performance of TADboost is compared against various popular ML (NN, BAG, NB, and SVM) models. Simulated result reveals that the suggested classifiers outperform other compared ML classifiers for fuel classification with the classification accuracy, precision, recall, F1-score, and kappa as 0.9659, 0.9671, 0.9449, 0.9558, and 0.9482, respectively.

关键词： Training Support vector machines Accuracy Biological system modeling Simulation Coal Linear programming Biomass Security Optimization

来源：评论

学校读者我要写书评

暂无评论

Electromagnetic characteristics of shape memory spring

Electromagnetic characteristics of shape memory spring

引用

International Conference on Processing and Characterization of Materials, ICPCM 2018

作者： Devashena, T. Dhanalakshmi, K. Dept. of Instrumentation and Control Engineering National Institute of Technology Tiruchirappalli India

ISBN: (纸本)9783035715033

Electric impedance is widely used in imaging and detection techniques. The applications range from non-destructive testing, structural health monitoring, and geophysical imaging to medical imaging. The frequency of the signal used for the measurement ranges from less than 1 Hz to about 1 GHz. This paper addresses the measurement and evaluation of the phase-dependent electrical resistance, inductance, capacitance and impedance of a shape memory alloy (SMA) spring (BMX 150, Toki Corporation). The material characteristics can be obtained by means of their electromechanical impedance. Experimental procedures are implemented and the electrical characteristics are obtained for a wide range of frequency. The electrical resistance, inductance, impedances of the austenite and martensite phase are determined, also the quality factor of the Bio Metal coil. to be (9.465 – 9.95) Ω and (10.358 – 10.8) Ω, (0.458 – 0.38) µH and (0.458 – 0.36) µH and, (9.47 – 10.24) Ω and (10.36 – 11.11) Ω respectively for the frequency range of 100 kHz-1MHz. The quality factor of the Bio Metal ranges between 0.03 and 0.2 during heating and, 0.028 and 0.022 during the cooling phase. The experimental results herein show that an equivalent circuit of the SMA spring is a series resistor-inductor circuit with a parasitic capacitance effect. The electromagnetic behaviour of SMA is determined using a finite element tool. © 2020 Trans Tech Publications Ltd, Switzerland.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

Development of Vehicle Dynamic Plant Model and Embedded Co-Simulation with ARM Platform

Development of Vehicle Dynamic Plant Model and Embedded Co-S...

引用

International Conference on Power Electronic Drives

作者： Dayaram Sonawane Sandeep D. Hanwate Pramod Ubare R. N. Marathe G. Srinivasa Rao Manish Sahu Dept. Instrumentation and Control College of Engineering Pune Pune India Vehicle R&D Establishment Ahmednagar India

In this paper, a Vehicle dynamic 14 Degree of Freedom(DoF) plant model is developed, the performance of the developed model is tested in MATLAB simulation and validated using CarSim software. The objective of the vehicle model is to assist and assess new or modified light motor vehicles (LMVs) while they are in the developing stage. The architecture is to increase modeling flexibility and allow for quick adaptation to new vehicle designs. Minimized inter dependencies exist between model subsystems such as Steering model, Wheel model, Suspension model, Roll model, and tire model. This a longitudinal and lateral model, further tested for straight breaking, Inferential torque measurement on real LMV model. Additionally, the developed model is implemented on the Embedded ARM (STM32F746) Platform by creating, C-code to solve the model in order to assess the feasibility of hardware implementation. Furthermore, the model is also tested on vehicle test-bench developed by VRDE.

关键词： Adaptation models Analytical models Suspensions (mechanical systems) Wheels Mathematical models Hardware Tires

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Different Adaptive control Strategies in Noise Cancellation Applications 4

Comparative Study of Different Adaptive Control Strategies i...

引用

4th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2020

作者： Dabhade, Amruta Madhukar Kanjalkar, Pramod Vishwakarma Institute of Technology Dept. of Instrumentation and Control Engineering Pune India

ISBN: (纸本)9781728163871

In this paper, the system identification and noise cancellation has been done and further the adaptive control algorithms like LMS(Least mean square),NLMS(normalized least mean square),NLMF(normalized least mean forth) and RLS(recursive least square) filters are compared. System identification identifies an unknown system given an input and output. It is used in active vibration and noise control applications. The LMS algorithm has lowest computations involved than all other ones. RLS is a computationally complex filter algorithm but it works more efficiently. In all of these filter algorithms, the weight coefficient is continuously updated until the convergence is reached. These algorithms are implemented and are compared by using parameters such as MSE (mean square error), PSNR (peak signal to noise ratio), convergence, complexity and accuracy. © 2020 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Mapless Navigation with Deep Reinforcement Learning based on The Convolutional Proximal Policy Optimization Network

Mapless Navigation with Deep Reinforcement Learning based on...

引用

International Conference on Big Data and Smart Computing (BIGCOMP)

作者： Nguyen Duc Toan Kim Gon Woo Dept. of Control and Robot Engineering Cheongju Chungbuk Korea

ISBN: (数字)9781728189246

ISBN: (纸本)9781728189253

In recent years, mapless navigation with a deep reinforcement learning approach in Autonomous Mobile robot has shown a considerable benefit in improving robot behavior flexibility. Specifically, the robot adapts to complex constraints and performs well in various environments without the need for a predetermined map and route plan. However, several previous studies show a lack of stability in the training of deep reinforcement learning networks for mapless navigation. Moreover, the exploration and exploitation in a specific work environment play an essential role in improving mapless navigation performance, which needs to be carefully considered. From the aforementioned issues, as well as inspired by the Proximal Policy optimization algorithm has shown that it does not only evaluates the advantages and disadvantages of policy but also prevents the policy from changing too much after each time weight update. In this paper, we propose to build a Convolutional Proximal Policy optimization network for the Mapless Navigation problem. Furthermore, the use of Boltzmann's policy to help balance exploration and exploitation also contributes to the robot's ability to explore more deeply in complex environments, and the performance of the mapless navigation problem is also significantly improved.

关键词： Training Navigation Conferences Reinforcement learning Big Data Mobile robots Optimization

来源：评论

学校读者我要写书评

暂无评论

Design of Fractional Order controller for Wood-Berry distillation column 17

Design of Fractional Order Controller for Wood-Berry distill...

引用

17th IEEE India Council International Conference, INDICON 2020

作者： Kumar, Rishu Anand, Satyam Khulbey, Ashish Nath Jha, Amar Netaji Subhas University of Technology Dept. of Instrumentation and Control Engineering Delhi India

ISBN: (纸本)9781728169163

In this paper, the control of the Wood-Berry distillation column is proposed using the Fractional Order PID (FOPID) controller, which is tuned by using Big Bang - Big Crunch (BB-BC) algorithm. The results obtained by tuning the parameters of the FOPID controller are compared to the results obtained after tuning the parameters of the PID controller using the Big Bang - Big Crunch (BB-BC) algorithm, Artificial Bee Colony (ABC) algorithm, and Particle Swarm Optimization (PSO) algorithm. © 2020 IEEE.

关键词： Distillation columns

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：