scholarly journals Data-Driven Channel Pruning towards Local Binary Convolution Inverse Bottleneck Network Based on Squeeze-and-Excitation Optimization Weights

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1329
Author(s):  
Duo Feng ◽  
Fuji Ren
Keyword(s):  
Small Parameter ◽  
Image Classification ◽  
Recognition Accuracy ◽  
Data Driven ◽  
Model Parameters ◽  
Model Based ◽  
Pruning Method ◽  
Convolution Model ◽  
Weight Value ◽  
Classification Database

This paper proposed a model pruning method based on local binary convolution (LBC) and squeeze-and-excitation (SE) optimization weights. We first proposed an efficient deep separation convolution model based on the LBC kernel. By expanding the number of LBC kernels in the model, we have trained a larger model with better results, but more parameters and slower calculation speed. Then, we extract the SE optimization weight value of each SE module according to the data samples and score the LBC kernel accordingly. Based on the score of each LBC kernel corresponding to the convolution channel, we performed channel-based model pruning, which greatly reduced the number of model parameters and accelerated the calculation speed. The model pruning method proposed in this paper is verified in the image classification database. Experiments show that, in the model using the LBC kernel, as the number of LBC kernels increases, the recognition accuracy will increase. At the same time, the experiment also proved that the recognition accuracy is maintained at a similar level in the small parameter model after channel-based model pruning by the SE optimization weight value.

scholarly journals A New Multi-Scale Convolutional Model Based on Multiple Attention for Image Classification

2019 ◽  
Vol 10 (1) ◽  
pp. 101 ◽  
Author(s):  
Yadong Yang ◽  
Chengji Xu ◽  
Feng Dong ◽  
Xiaofeng Wang
Keyword(s):  
Image Classification ◽  
Attention Mechanism ◽  
Natural Scenes ◽  
Significant Information ◽  
Convolutional Networks ◽  
Multi Scale ◽  
Model Based ◽  
Convolution Model ◽  
Grouping Method ◽  
Feature Expression

Computer vision systems are insensitive to the scale of objects in natural scenes, so it is important to study the multi-scale representation of features. Res2Net implements hierarchical multi-scale convolution in residual blocks, but its random grouping method affects the robustness and intuitive interpretability of the network. We propose a new multi-scale convolution model based on multiple attention. It introduces the attention mechanism into the structure of a Res2-block to better guide feature expression. First, we adopt channel attention to score channels and sort them in descending order of the feature’s importance (Channels-Sort). The sorted residual blocks are grouped and intra-block hierarchically convolved to form a single attention and multi-scale block (AMS-block). Then, we implement channel attention on the residual small blocks to constitute a dual attention and multi-scale block (DAMS-block). Introducing spatial attention before sorting the channels to form multi-attention multi-scale blocks(MAMS-block). A MAMS-convolutional neural network (CNN) is a series of multiple MAMS-blocks. It enables significant information to be expressed at more levels, and can also be easily grafted into different convolutional structures. Limited by hardware conditions, we only prove the validity of the proposed ideas through convolutional networks of the same magnitude. The experimental results show that the convolution model with an attention mechanism and multi-scale features is superior in image classification.

scholarly journals Applications of predictive maintenance techniques in industrial systems

2011 ◽  
Vol 8 (3) ◽  
pp. 263-279 ◽  
Author(s):  
Aleksandra Marjanovic ◽  
Goran Kvascev ◽  
Predrag Tadic ◽  
Zeljko Djurovic
Keyword(s):  
Power Plants ◽  
Hypothesis Test ◽  
Moving Average ◽  
Thermal Power ◽  
Cost Savings ◽  
Data Driven ◽  
Model Parameters ◽  
Model Based ◽  
Level Sensor ◽  
Arma Modeling

Prognostic methods represent a new methodology for system maintenance which offers significant time and cost savings. The paper offers a short overview of the available prognosis techniques and proposes the implementation of one model-based and one data-driven method. As a representative of the model-based methods the autoregressive moving average (ARMA) modeling approach is chosen. The estimated model parameters are further used for implementing the early change detector which is realized as a Neyman-Pearson hypothesis test. On the other hand, hidden Markov model (HMM) based prognosis illustrates the use of data-driven techniques. Using the cross-correlation input-output functions, HMM prognosis algorithm is proposed, as a suitable way of timely detection. Both techniques were implemented to detect performance changes of the water level sensor in a steam separator system in thermal power plants.

scholarly journals The New Trend of State Estimation: From Model-Driven to Hybrid-Driven Methods

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2085
Author(s):  
Xue-Bo Jin ◽  
Ruben Jonhson Robert RobertJeremiah ◽  
Ting-Li Su ◽  
Yu-Ting Bai ◽  
Jian-Lei Kong
Keyword(s):  
Kalman Filter ◽  
State Estimation ◽  
Future Development ◽  
Data Driven ◽  
Estimation Methods ◽  
Multiple Model ◽  
Development Trends ◽  
Research Results ◽  
Model Driven ◽  
Model Based

State estimation is widely used in various automated systems, including IoT systems, unmanned systems, robots, etc. In traditional state estimation, measurement data are instantaneous and processed in real time. With modern systems’ development, sensors can obtain more and more signals and store them. Therefore, how to use these measurement big data to improve the performance of state estimation has become a hot research issue in this field. This paper reviews the development of state estimation and future development trends. First, we review the model-based state estimation methods, including the Kalman filter, such as the extended Kalman filter (EKF), unscented Kalman filter (UKF), cubature Kalman filter (CKF), etc. Particle filters and Gaussian mixture filters that can handle mixed Gaussian noise are discussed, too. These methods have high requirements for models, while it is not easy to obtain accurate system models in practice. The emergence of robust filters, the interacting multiple model (IMM), and adaptive filters are also mentioned here. Secondly, the current research status of data-driven state estimation methods is introduced based on network learning. Finally, the main research results for hybrid filters obtained in recent years are summarized and discussed, which combine model-based methods and data-driven methods. This paper is based on state estimation research results and provides a more detailed overview of model-driven, data-driven, and hybrid-driven approaches. The main algorithm of each method is provided so that beginners can have a clearer understanding. Additionally, it discusses the future development trends for researchers in state estimation.

scholarly journals A Model-Based Tool for Assessing the Impact of Land Use Change Scenarios on Flood Risk in Small-Scale River Systems—Part 1: Pre-Processing of Scenario Based Flood Characteristics for the Current State of Land Use

Hydrology ◽  
2021 ◽  
Vol 8 (3) ◽  
pp. 102
Author(s):  
Frauke Kachholz ◽  
Jens Tränckner
Keyword(s):  
Land Use ◽  
River Flow ◽  
Land Use Changes ◽  
Small Rivers ◽  
Small Scale ◽  
Model Parameters ◽  
Ungauged Catchments ◽  
Model Based ◽  
Current State ◽  
The Impact

Land use changes influence the water balance and often increase surface runoff. The resulting impacts on river flow, water level, and flood should be identified beforehand in the phase of spatial planning. In two consecutive papers, we develop a model-based decision support system for quantifying the hydrological and stream hydraulic impacts of land use changes. Part 1 presents the semi-automatic set-up of physically based hydrological and hydraulic models on the basis of geodata analysis for the current state. Appropriate hydrological model parameters for ungauged catchments are derived by a transfer from a calibrated model. In the regarded lowland river basins, parameters of surface and groundwater inflow turned out to be particularly important. While the calibration delivers very good to good model results for flow (Evol =2.4%, R = 0.84, NSE = 0.84), the model performance is good to satisfactory (Evol = −9.6%, R = 0.88, NSE = 0.59) in a different river system parametrized with the transfer procedure. After transferring the concept to a larger area with various small rivers, the current state is analyzed by running simulations based on statistical rainfall scenarios. Results include watercourse section-specific capacities and excess volumes in case of flooding. The developed approach can relatively quickly generate physically reliable and spatially high-resolution results. Part 2 builds on the data generated in part 1 and presents the subsequent approach to assess hydrologic/hydrodynamic impacts of potential land use changes.

scholarly journals Multi-Inputs and Multi-Outputs equivalent model based on data driven controller for a robotic system

2020 ◽  
Vol 53 (2) ◽  
pp. 9784-9789
Author(s):  
Josué Gómez ◽  
Chidentree Treesatayapun ◽  
América Morales
Keyword(s):  
Robotic System ◽  
Data Driven ◽  
Equivalent Model ◽  
Model Based

Data-driven Model-based Detection of Malicious Insiders via Physical Access Logs

2019 ◽  
Vol 29 (4) ◽  
pp. 1-25 ◽  
Author(s):  
Carmen Cheh ◽  
Uttam Thakore ◽  
Ahmed Fawaz ◽  
Binbin Chen ◽  
William G. Temple ◽  
...  
Keyword(s):  
Data Driven ◽  
Model Based ◽  
Malicious Insiders ◽  
Access Logs ◽  
Physical Access

scholarly journals A DATA-DRIVEN APPROACH TO USER-EXPERIENCE-FOCUSED MODEL-BASED ROADMAPPING FOR NEW PRODUCT PLANNING

2021 ◽  
Vol 1 ◽  
pp. 61-70
Author(s):  
Ilia Iuskevich ◽  
Andreas-Makoto Hein ◽  
Kahina Amokrane-Ferka ◽  
Abdelkrim Doufene ◽  
Marija Jankovic
Keyword(s):  
New Product Development ◽  
User Experience ◽  
Planning Process ◽  
New Product ◽  
Data Driven ◽  
User Needs ◽  
User Testing ◽  
Model Based ◽  
Data Driven Approach ◽  
To Receive

AbstractUser experience (UX) focused business needs to survive and plan its new product development (NPD) activities in a highly turbulent environment. The latter is a function of volatile UX and technology trends, competition, unpredictable events, and user needs uncertainty. To address this problem, the concept of design roadmapping has been proposed in the literature. It was argued that tools built on the idea of design roadmapping have to be very flexible and data-driven (i.e., be able to receive feedback from users in an iterative manner). At the same time, a model-based approach to roadmapping has emerged, promising to achieve such flexibility. In this work, we propose to incorporate design roadmapping to model-based roadmapping and integrate it with various user testing approaches into a single tool to support a flexible data-driven NPD planning process.

Sign in / Sign up

Export Citation Format

Share Document