PET block detector calibration using subtractive clustering algorithm and comparison with hough transform algorithm

2016 ◽  
Vol 59 (1) ◽  
pp. 75-81
Author(s):  
S. Z. Islami rad ◽  
R. GholipourPeyvandi ◽  
E. Tavakoli
Keyword(s):  
Hough Transform ◽  
Clustering Algorithm ◽  
Subtractive Clustering ◽  
Detector Calibration

scholarly journals Application of Neural Network Models and ANFIS for Water Level Forecasting of the Salve Faccha Dam in the Andean Zone in Northern Ecuador

Water ◽  
2021 ◽  
Vol 13 (15) ◽  
pp. 2011
Author(s):  
Pablo Páliz Larrea ◽  
Xavier Zapata Ríos ◽  
Lenin Campozano Parra
Keyword(s):  
Neural Network ◽  
Water Level ◽  
Clustering Algorithm ◽  
Network Models ◽  
Water Levels ◽  
Subtractive Clustering ◽  
Neural Network Models ◽  
Reservoir Water ◽  
Reservoir Water Level ◽  
Maximum Delay

Despite the importance of dams for water distribution of various uses, adequate forecasting on a day-to-day scale is still in great need of intensive study worldwide. Machine learning models have had a wide application in water resource studies and have shown satisfactory results, including the time series forecasting of water levels and dam flows. In this study, neural network models (NN) and adaptive neuro-fuzzy inference systems (ANFIS) models were generated to forecast the water level of the Salve Faccha reservoir, which supplies water to Quito, the Capital of Ecuador. For NN, a non-linear input–output net with a maximum delay of 13 days was used with variation in the number of nodes and hidden layers. For ANFIS, after up to four days of delay, the subtractive clustering algorithm was used with a hyperparameter variation from 0.5 to 0.8. The results indicate that precipitation was not influencing input in the prediction of the reservoir water level. The best neural network and ANFIS models showed high performance, with a r > 0.95, a Nash index > 0.95, and a RMSE < 0.1. The best the neural network model was t + 4, and the best ANFIS model was model t + 6.

Calibration of a micro-electro mechanical system-based accelerometer for vehicle navigation

2018 ◽  
Vol 233 (2) ◽  
pp. 554-560 ◽  
Author(s):  
A Ghaffari ◽  
A Khodayari ◽  
S Nosoudi ◽  
S Arefnezhad
Keyword(s):  
Mechanical System ◽  
Clustering Algorithm ◽  
Moving Objects ◽  
Inertial Sensors ◽  
Low Cost ◽  
Micro Electro Mechanical System ◽  
Subtractive Clustering ◽  
Measured Velocity ◽  
Preliminary Model ◽  
Dynamic Errors

Micro-electro mechanical system-based inertial sensors have broad applications in moving objects including in vehicles for navigation purposes. The low-cost micro-electro mechanical system sensors are normally subject to high dynamic errors such as linear or nonlinear bias, misalignment errors and random noises. In the class of low cost sensors, keeping the accuracy at a reasonable range has always been challenging for engineers. In this paper, a novel method for calibrating low-cost micro-electro mechanical system accelerometers is presented based on soft computing approaches. The method consists of two steps. In the first step, a preliminary model for error sources is presented based on fuzzy subtractive clustering algorithm. This model is then improved using adaptive neuro-fuzzy systems. A Kalman filter is also used to calculate the vehicle velocity and its position based on calibrated measured acceleration. The performance of the presented approach has been validated in the simulated and real experimental driving scenarios. The results show that this method can improve the accuracy of the accelerometer output, measured velocity and position of the vehicle by 79.11%, 97.63% and 99.28%, in the experimental test, respectively. The presented procedure can be used in collision avoidance and emergency brake assist systems.

scholarly journals Multimode Operating Performance Visualization and Nonoptimal Cause Identification

Processes ◽  
2020 ◽  
Vol 8 (1) ◽  
pp. 123 ◽  
Author(s):  
Yuhui Ying ◽  
Zhi Li ◽  
Minglei Yang ◽  
Wenli Du
Keyword(s):  
Clustering Algorithm ◽  
Expert Knowledge ◽  
Operating Performance ◽  
Principal Component ◽  
Assessment Method ◽  
Subtractive Clustering ◽  
Self Organizing Map ◽  
Visual Model ◽  
Performance Visualization ◽  
Traditional Performance

In the traditional performance assessment method, different modes of data are classified mainly by expert knowledge. Thus, human interference is highly probable. The traditional method is also incapable of distinguishing transition data from steady-state data, which reduces the accuracy of the monitor model. To solve these problems, this paper proposes a method of multimode operating performance visualization and nonoptimal cause identification. First, multimode data identification is realized by subtractive clustering algorithm (SCA), which can reduce human influence and eliminate transition data. Then, the multi-space principal component analysis (MsPCA) is used to characterize the independent characteristics of different datasets, which enhances the robustness of the model with respect to the performance of independent variables. Furthermore, a self-organizing map (SOM) is used to train these characteristics and map them into a two-dimensional plane, by which the visualization of the process monitor is realized. For the online assessment, the operating performance of the current process is evaluated according to the projection position of the data on the visual model. Then, the cause of the nonoptimal performance is identified. Finally, the Tennessee Eastman (TE) process is used to verify the effectiveness of the proposed method.

Generator Coherency and Network Partitioning for Dynamic Equivalencing Using Subtractive Clustering Algorithm

2018 ◽  
Vol 12 (4) ◽  
pp. 3085-3095 ◽  
Author(s):  
Mohammad Hossein Rezaeian ◽  
Saeid Esmaeili ◽  
Roohollah Fadaeinedjad
Keyword(s):  
Clustering Algorithm ◽  
Subtractive Clustering ◽  
Network Partitioning

Evaluate Fabric Wrinkle Grade Based on Subtractive Clustering Adaptive Network Fuzzy Inference Systems

2011 ◽  
Vol 332-334 ◽  
pp. 1505-1510
Author(s):  
Xiao Bo Yang
Keyword(s):  
Network Inference ◽  
Clustering Algorithm ◽  
Fuzzy Inference ◽  
Real Data ◽  
Subtractive Clustering ◽  
Fuzzy Inference Systems ◽  
Adaptive Network ◽  
Inference System ◽  
Fuzzy Neural ◽  
Inference Systems

In this paper, a new method of subtractive clustering adaptive network fuzzy inference systems is proposed to assess degree of wrinkle in the fabric. The clustering center can be gotten through subtractive clustering algorithm, which is the base to set up adaptive network inference systems. Firstly, subtractive clustering algorithm is used to confirm the structure of fuzzy neural network, then, fuzzy inference system is used to process pattern recognition. Finally, four kinds of fabric wrinkle feature parameters are used to verify the results on real fabric. The results show the applicability of the proposed method to real data.

A NOVEL VALIDITY INDEX FOR THE SUBTRACTIVE CLUSTERING ALGORITHM

2011 ◽  
Vol 25 (04) ◽  
pp. 547-563 ◽  
Author(s):  
HORNG-LIN SHIEH ◽  
CHENG-CHIEN KUO
Keyword(s):  
Clustering Algorithm ◽  
Optimal Number ◽  
Subtractive Clustering ◽  
Cluster Validity ◽  
Cluster Validity Index ◽  
Validity Index ◽  
Simple Method ◽  
Data Points ◽  
Few Data ◽  
Performance Results

This paper proposes a new validity index for the subtractive clustering (SC) algorithm. The subtractive clustering algorithm proposed by Chiu is an effective and simple method for identifying the cluster centers of sampling data based on the concept of a density function. The SC algorithm continually produces the cluster centers until the final potential compared with the original is less than a predefined threshold. The procedure is terminated when there are only a few data points around the most recent cluster. The choice of the threshold is an important factor affecting the clustering results: if it is too large, then too few data points will be accepted as cluster centers; if it is too small, then too many cluster centers will be generated. In this paper, a modified SC algorithm for data clustering based on a cluster validity index is proposed to obtain the optimal number of clusters. Six examples show that the proposed index achieves better performance results than other cluster validities do.

Sign in / Sign up

Export Citation Format

Share Document