scholarly journals Sensorless Estimation Based on Neural Networks Trained with the Dynamic Response Points

Sensors ◽  
2021 ◽  
Vol 21 (20) ◽  
pp. 6719
Author(s):  
Omar Rodríguez-Abreo ◽  
Francisco Antonio Castillo Velásquez ◽  
Jonny Paul Zavala de Paz ◽  
José Luis Martínez Godoy ◽  
Crescencio Garcia Guendulain
Keyword(s):  
Neural Networks ◽  
Transfer Function ◽  
Dynamic Response ◽  
High Performance ◽  
Response Prediction ◽  
Stable System ◽  
Network Systems ◽  
Multiple Systems ◽  
Data Points ◽  
Basic Characteristics

In the present work, a neuronal dynamic response prediction system is shown to estimate the response of multiple systems remotely without sensors. For this, a set of Neural Networks and the response to the step of a stable system is used. Six basic characteristics of the dynamic response were extracted and used to calculate a Transfer Function equivalent to the dynamic model. A database with 1,500,000 data points was created to train the network system with the basic characteristics of the dynamic response and the Transfer Function that causes it. The contribution of this work lies in the use of Neural Network systems to estimate the behavior of any stable system, which has multiple advantages compared to typical linear regression techniques since, although the training process is offline, the estimation can perform in real time. The results show an average 2% MSE error for the set of networks. In addition, the system was tested with physical systems to observe the performance with practical examples, achieving a precise estimation of the output with an error of less than 1% for simulated systems and high performance in real signals with the typical noise associated due to the acquisition system.

scholarly journals Computational Complexity Reduction of Neural Networks of Brain Tumor Image Segmentation by Introducing Fermi–Dirac Correction Functions

Entropy ◽  
2021 ◽  
Vol 23 (2) ◽  
pp. 223
Author(s):  
Yen-Ling Tai ◽  
Shin-Jhe Huang ◽  
Chien-Chang Chen ◽  
Henry Horng-Shing Lu
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Computational Complexity ◽  
High Performance ◽  
Low Cost ◽  
Structural Complexity ◽  
Correction Function ◽  
Computational Time ◽  
Learning Methods ◽  
Band Theory

Nowadays, deep learning methods with high structural complexity and flexibility inevitably lean on the computational capability of the hardware. A platform with high-performance GPUs and large amounts of memory could support neural networks having large numbers of layers and kernels. However, naively pursuing high-cost hardware would probably drag the technical development of deep learning methods. In the article, we thus establish a new preprocessing method to reduce the computational complexity of the neural networks. Inspired by the band theory of solids in physics, we map the image space into a noninteraction physical system isomorphically and then treat image voxels as particle-like clusters. Then, we reconstruct the Fermi–Dirac distribution to be a correction function for the normalization of the voxel intensity and as a filter of insignificant cluster components. The filtered clusters at the circumstance can delineate the morphological heterogeneity of the image voxels. We used the BraTS 2019 datasets and the dimensional fusion U-net for the algorithmic validation, and the proposed Fermi–Dirac correction function exhibited comparable performance to other employed preprocessing methods. By comparing to the conventional z-score normalization function and the Gamma correction function, the proposed algorithm can save at least 38% of computational time cost under a low-cost hardware architecture. Even though the correction function of global histogram equalization has the lowest computational time among the employed correction functions, the proposed Fermi–Dirac correction function exhibits better capabilities of image augmentation and segmentation.

scholarly journals Faking Signals to Fool Deep Neural Networks in AMC via Few Data Points

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Hongbin Ma ◽  
Shuyuan Yang ◽  
Guangjun He ◽  
Ruowu Wu ◽  
Xiaojun Hao ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Data Points ◽  
Few Data

scholarly journals Systems biology informed neural networks (SBINN) predict response and novel combinations for PD-1 checkpoint blockade

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Michelle Przedborski ◽  
Munisha Smalley ◽  
Saravanan Thiyagarajan ◽  
Aaron Goldman ◽  
Mohammad Kohandel
Keyword(s):  
Neural Networks ◽  
Systems Biology ◽  
Clinical Data ◽  
Treatment Protocol ◽  
Response Prediction ◽  
Clinical Findings ◽  
Patient Specific ◽  
Patient Response ◽  
Triple Combination Therapy ◽  
Parameter Values

AbstractAnti-PD-1 immunotherapy has recently shown tremendous success for the treatment of several aggressive cancers. However, variability and unpredictability in treatment outcome have been observed, and are thought to be driven by patient-specific biology and interactions of the patient’s immune system with the tumor. Here we develop an integrative systems biology and machine learning approach, built around clinical data, to predict patient response to anti-PD-1 immunotherapy and to improve the response rate. Using this approach, we determine biomarkers of patient response and identify potential mechanisms of drug resistance. We develop systems biology informed neural networks (SBINN) to calculate patient-specific kinetic parameter values and to predict clinical outcome. We show how transfer learning can be leveraged with simulated clinical data to significantly improve the response prediction accuracy of the SBINN. Further, we identify novel drug combinations and optimize the treatment protocol for triple combination therapy consisting of IL-6 inhibition, recombinant IL-12, and anti-PD-1 immunotherapy in order to maximize patient response. We also find unexpected differences in protein expression levels between response phenotypes which complement recent clinical findings. Our approach has the potential to aid in the development of targeted experiments for patient drug screening as well as identify novel therapeutic targets.

scholarly journals Communication Failure Resilient Distributed Neural Network for Edge Devices

Electronics ◽  
2021 ◽  
Vol 10 (14) ◽  
pp. 1614
Author(s):  
Jonghun Jeong ◽  
Jong Sung Park ◽  
Hoeseok Yang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
High Performance ◽  
State Of The Art ◽  
Wearable Devices ◽  
Communication Failure ◽  
Canadian Institute ◽  
Multiple Devices ◽  
Knowledge Distillation ◽  
Partitioning Technique

Recently, the necessity to run high-performance neural networks (NN) is increasing even in resource-constrained embedded systems such as wearable devices. However, due to the high computational and memory requirements of the NN applications, it is typically infeasible to execute them on a single device. Instead, it has been proposed to run a single NN application cooperatively on top of multiple devices, a so-called distributed neural network. In the distributed neural network, workloads of a single big NN application are distributed over multiple tiny devices. While the computation overhead could effectively be alleviated by this approach, the existing distributed NN techniques, such as MoDNN, still suffer from large traffics between the devices and vulnerability to communication failures. In order to get rid of such big communication overheads, a knowledge distillation based distributed NN, called Network of Neural Networks (NoNN), was proposed, which partitions the filters in the final convolutional layer of the original NN into multiple independent subsets and derives smaller NNs out of each subset. However, NoNN also has limitations in that the partitioning result may be unbalanced and it considerably compromises the correlation between filters in the original NN, which may result in an unacceptable accuracy degradation in case of communication failure. In this paper, in order to overcome these issues, we propose to enhance the partitioning strategy of NoNN in two aspects. First, we enhance the redundancy of the filters that are used to derive multiple smaller NNs by means of averaging to increase the immunity of the distributed NN to communication failure. Second, we propose a novel partitioning technique, modified from Eigenvector-based partitioning, to preserve the correlation between filters as much as possible while keeping the consistent number of filters distributed to each device. Throughout extensive experiments with the CIFAR-100 (Canadian Institute For Advanced Research-100) dataset, it has been observed that the proposed approach maintains high inference accuracy (over 70%, 1.53× improvement over the state-of-the-art approach), on average, even when a half of eight devices in a distributed NN fail to deliver their partial inference results.

Model-Independent Control of a Flexible-Joint Robot Manipulator

2009 ◽  
Vol 131 (4) ◽  
Author(s):  
Withit Chatlatanagulchai ◽  
Peter H. Meckl
Keyword(s):  
Neural Networks ◽  
Open Problem ◽  
High Performance ◽  
Robot Manipulator ◽  
Intrinsic Property ◽  
Variable Structure ◽  
System Model ◽  
Control Input ◽  
Control Laws ◽  
Flexible Joint

Flexibility at the joint of a manipulator is an intrinsic property. Even “rigid-joint” robots, in fact, possess a certain amount of flexibility. Previous experiments confirmed that joint flexibility should be explicitly included in the model when designing a high-performance controller for a manipulator because the flexibility, if not dealt with, can excite system natural frequencies and cause severe damage. However, control design for a flexible-joint robot manipulator is still an open problem. Besides being described by a complicated system model for which the passivity property does not hold, the manipulator is also underactuated, that is, the control input does not drive the link directly, but through the flexible dynamics. Our work offers another possible solution to this open problem. We use three-layer neural networks to represent the system model. Their weights are adapted in real time and from scratch, which means we do not need the mathematical model of the robot in our control algorithm. All uncertainties are handled by variable-structure control. Backstepping structure allows input efforts to be applied to each subsystem where they are needed. Control laws to adjust all adjustable parameters are devised using Lyapunov’s second method to ensure that error trajectories are globally uniformly ultimately bounded. We present two state-feedback schemes: first, when neural networks are used to represent the unknown plant, and second, when neural networks are used to represent the unknown parts of the control laws. In the former case, we also design an observer to enable us to design a control law using only output signals—the link positions. We use simulations to compare our algorithms with some other well-known techniques. We use experiments to demonstrate the practicality of our algorithms.

Wavelets as activation functions in Neural Networks

2021 ◽  
pp. 1-11
Author(s):  
Oscar Herrera ◽  
Belém Priego
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
High Performance ◽  
Research Area ◽  
Experimental Results ◽  
Activation Functions ◽  
Hyperbolic Tangent ◽  
Open Research ◽  
Bounded Functions

Traditionally, a few activation functions have been considered in neural networks, including bounded functions such as threshold, sigmoidal and hyperbolic-tangent, as well as unbounded ReLU, GELU, and Soft-plus, among other functions for deep learning, but the search for new activation functions still being an open research area. In this paper, wavelets are reconsidered as activation functions in neural networks and the performance of Gaussian family wavelets (first, second and third derivatives) are studied together with other functions available in Keras-Tensorflow. Experimental results show how the combination of these activation functions can improve the performance and supports the idea of extending the list of activation functions to wavelets which can be available in high performance platforms.

A simulation study of nonideal mixing effect on the dynamic response of an exothermic CSTR with Cholette’s model

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Chane-Yuan Yang ◽  
Yu-Shu Chien ◽  
Jun-Hong Chou
Keyword(s):  
Transfer Function ◽  
Dynamic Response ◽  
The Other ◽  
System Stability ◽  
Mixing Effect ◽  
Characteristic Roots ◽  
Mixing Parameter ◽  
Perfect Mixing ◽  
And Control ◽  
Inverse Response

Abstract The study of nonideal mixing effect on the dynamic behaviors of CSTRs has very rarely been published in the literature. In this work, Cholette’s model is employed to explore the nonideal mixing effect on the dynamic response of a nonisothermal CSTR. The analysis shows that the mixing parameter n (the fraction of the feed entering the zone of perfect mixing) and m (the fraction of the total volume of the reactor), indeed affect the characteristic roots of transfer function of a real CSTR, which determine the system stability. On the other hand, the inverse response and overshoot response are also affected by the nonideal mixing in a nonisothemal CSTR. These results are of much help for the design and control of a real CSTR.

Sign in / Sign up

Export Citation Format

Share Document