Inertial measurement unit–based cricket stroke improviser using polynomial kernel support vector machines

2021 ◽  
pp. 095440622110574
Author(s):  
N Nithya ◽  
G Nallavan
Keyword(s):  
Embedded System ◽  
Real Time ◽  
Training Session ◽  
Cloud Services ◽  
Measurement Unit ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Sports Industry ◽  
Machine Learning Model ◽  
Kernel Support Vector Machines

Wearable devices have now become virtual assistants, and the sports industry also aims in technological integration. The objective of this research article is to introduce a wearable device to detect and record the movement of a cricket player during his training session. The designed system collects the displacement and rotational information through a combination of accelerometer and gyroscope placed on the cricket bat. We propose a data-driven machine learning model which takes raw analog data as input for classifying the strokes. The algorithm used is the polynomial support vector machine, a supervised classification algorithm with 300 independent variables to enable accurate and real-time stroke classification. The system has a dedicated user interface for accessing these real-time details. This wearable embedded system does not require any cloud services as the complex analyses are performed in the processor itself. The player and the coach can get visual reference support, and the mistakes can be corrected during the training period itself. The device can detect the arm action of a cricket player with a success rate of 97%. The hardware is powered using a 10,000 mAh rechargeable battery.

A New Topology for Artificial Higher Order Neural Networks

2009 ◽  
pp. 430-441 ◽  
Author(s):  
Zhao Lu ◽  
Leang-san Shieh ◽  
Guanrong Chen
Keyword(s):  
Neural Networks ◽  
Network Performance ◽  
System Modeling ◽  
Higher Order ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Risk Minimization ◽  
Higher Order Neural Networks ◽  
Hidden Layer ◽  
Kernel Support Vector Machines

Aiming to develop a systematic approach for optimizing the structure of artificial higher order neural networks (HONN) for system modeling and function approximation, a new HONN topology, namely polynomial kernel networks, is proposed in this chapter. Structurally, the polynomial kernel network can be viewed as a three-layer feedforward neural network with a special polynomial activation function for the nodes in the hidden layer. The new network is equivalent to a HONN; however, due to the underlying connections with polynomial kernel support vector machines, the weights and the structure of the network can be determined simultaneously using structural risk minimization. The advantage of the topology of the polynomial kernel network and the use of a support vector kernel expansion paves the way to represent nonlinear functions or systems, and underpins some advanced analysis of the network performance. In this chapter, from the perspective of network complexity, both quadratic programming and linear programming based training of the polynomial kernel network are investigated.

scholarly journals Evaluation of low degree polynomial kernel support vector machines for modelling Pore-water pressure responses

2016 ◽  
Vol 59 ◽  
pp. 04003
Author(s):  
Nuraddeen Muhammad Babangida ◽  
Muhammad Raza Ul Mustafa ◽  
Khamaruzaman Wan Yusuf ◽  
Mohamed Hasnain Isa ◽  
Imran Baig
Keyword(s):  
Support Vector Machines ◽  
Pore Water ◽  
Pore Water Pressure ◽  
Water Pressure ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Degree Polynomial ◽  
Low Degree ◽  
Vector Machines ◽  
Kernel Support Vector Machines

FACE RECOGNITION USING SUPPORT VECTOR MACHINES WITH LOCAL CORRELATION KERNELS

2002 ◽  
Vol 16 (01) ◽  
pp. 97-111 ◽  
Author(s):  
KWANG IN KIM ◽  
JIN HYUNG KIM ◽  
KEECHUL JUNG
Keyword(s):  
Face Recognition ◽  
Support Vector Machines ◽  
Real Time ◽  
Recognition Rate ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Local Correlation ◽  
Correlation Kernel ◽  
Vector Machines ◽  
The Face

This paper presents a real-time face recognition system. For the system to be real time, no external time-consuming feature extraction method is used, rather the gray-level values of the raw pixels that make up the face pattern are fed directly to the recognizer. In order to absorb the resulting high dimensionality of the input space, support vector machines (SVMs), which are known to work well even in high-dimensional space, are used as the face recognizer. Furthermore, a modified form of polynomial kernel (local correlation kernel) is utilized to take account of prior knowledge about facial structures and is used as the alternative feature extractor. Since SVMs were originally developed for two-class classification, their basic scheme is extended for multiface recognition by adopting one-per-class decomposition. In order to make a final classification from several one-per-class SVM outputs, a neural network (NN) is used as the arbitrator. Experiments with ORL database show a recognition rate of 97.9% and speed of 0.22 seconds per face with 40 classes.

Automated scaffolding safety analysis: strain feature investigation using support vector machines

2020 ◽  
Vol 47 (8) ◽  
pp. 921-928
Author(s):  
Sayan Sakhakarmi ◽  
Cristian Arteaga ◽  
JeeWoong Park ◽  
Chunhee Cho
Keyword(s):  
Real Time ◽  
Kernel Functions ◽  
Training Data ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Individual Member ◽  
Machine Learning Classification ◽  
Vector Machines ◽  
Potential Failure ◽  
Safety Cases

This study developed a methodology that can use real-time strain data for the assessment of scaffolding safety conditions. The researchers identified 23 safety cases of individual member failure with generic global failure for a four-bay, three-story scaffold model and used scaffold member strain values to identify potential failure cases. A computer simulation on the scaffold model generated the strain datasets required for classification with a support vector machine (SVM). The SVM classification demonstrated a stable prediction accuracy after training with a certain number of strain datasets. Furthermore, the 2nd order polynomial kernel function resulted in better prediction compared to other SVM kernel functions. These results imply that the real-time assessment of scaffolding structures is possible with a limited number of training data for machine-learning classification.

scholarly journals Tahapan Desain dan Implementasi Model Machine Learning untuk Sistem Tertanam

2020 ◽  
Vol 12 (2) ◽  
pp. 79-85
Author(s):  
Aminuddin Rizal
Keyword(s):  
Machine Learning ◽  
Embedded System ◽  
Support Vector ◽  
Recognition Experiment ◽  
Machine Learning Model ◽  
Hoeffding Tree ◽  
Simple Logistic ◽  
Stress Recognition ◽  
Simple Stress ◽  
Machine Learning Tool

machine learning and edge computing currently becomes popular technology used in any discipline. Flexibility and adapt to the problem are the main advantages of its technology. In this paper, we explain step-by-step way to make a lightweight machine learning model especially intended for embedded system application. We use open source machine learning tool called as Weka to design the model. Moreover, we performed a simple stress recognition experiment to make our own dataset for evaluation. We evaluate algorithm complexity and accuracy for different well-known classifier such as support vector machine, simple logistic and hoeffding tree.

scholarly journals Design, Development, and Deployment of Real-Time Sensor Fusion (CnW + EKF) for a Linux-Based Embedded System Using Qt-Anywhere

2018 ◽  
Vol 2018 ◽  
pp. 1-14 ◽  
Author(s):  
Felipe P. Vista ◽  
Kil To Chong
Keyword(s):  
Embedded System ◽  
Real Time ◽  
Sensor Fusion ◽  
Measurement Unit ◽  
Design Development ◽  
Time Operation ◽  
Global Positioning ◽  
Real Time Operation ◽  
Kalman Filter Algorithm ◽  
Electronic Compass

This paper describes the design, development, and implementation of a real-time sensor fusion system that utilizes the classification and weighing plus extended Kalman filter algorithm to derive heading for navigation using inexpensive sensors. This algorithm was previously tested only through postprocessing using MATLAB and is now reprogrammed using Qt and deployed on a Linux-based embedded board for real-time operation. Various data from inexpensive sensors such as global positioning system devices, an electronic compass, and an inertial measurement unit were utilized to ultimately derive a more reliable and accurate heading value. The algorithm flow can be described with the GPS values first being evaluated and classified which are then fused with the EC heading using classification and weighing, whose result is then passed through an EKF to fuse with the IMU data. Real-time tests and trials were done to prove the operational capability of the developed process. The complete setup and configuration processes of the systems for development and deployment via Qt are also provided for those interested to replicate the process.

scholarly journals An Approaching Machine Learning Model: Tile Inspection Case Study

2020 ◽  
Vol 4 (01) ◽  
pp. 12-22
Author(s):  
Murman Dwi Prasetio
Keyword(s):  
Machine Learning ◽  
Work Productivity ◽  
Basic Needs ◽  
Learning Model ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Machine Learning Model ◽  
Inspection Process ◽  
Image Test

Clothing, food, and shelter are three basic types of needs in our lives. If one of the basic needs is not met then there can be an imbalance in our lives. One of the basic needs is to build a house. House needs a tile or roof to cover of a building that can protect all weather influences. One company in Majalengka only uses fleeting vision in inspection process. This can result in a decrease in work productivity. This paper proposed an approach machine learning model for classification of defects was carried out in the inspection process. Feature extraction was performed using the Local Binary Pattern (LBP) method to obtain training features. The next stage is training (training) to the characteristics of training that has been obtained. Furthermore, the database obtained from the training results will be used to classify tile image test data using the Support Vector Machine (SVM) method. From the test results, the system is made capable of classifying defects of a maximum accuracy value of 63.21%. The results obtained are the best accuracy value generated is 76.67% with LBP parameters used are 256 × 256 cell size and radius 2. While for SVM parameters use Polynomial kernel type or RBF with OAA multiclass

scholarly journals Real time Drowsy Driver Detection using Polynomial Kernel based Support Vector Machine

2021 ◽  
Vol 9 (9) ◽  
pp. 1389-1396
Author(s):  
Makhan Ahirwar
Keyword(s):  
Machine Learning ◽  
Computer Vision ◽  
Support Vector Machine ◽  
Real Time ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Human Errors ◽  
Drowsiness Detection ◽  
Non Linear ◽  
Data Separation

Abstract: Casualty increases from road accidents day by day. There are so many reasons that accident causes and mostly due to human errors. Driver drowsiness is one of them. A small drowsiness may turn it into a big accident that resulted heavy casualties. If any of the system automatically detects the driver’s drowsiness and alert at real time may secure many lives. Drowsiness can be recognized by different situations such as by opening full mouth, by closing both the eyes and a combination of both. This may advised not to drive at drowsy state. There are various techniques through which drowsiness can be detected at real time but accuracy matters. OpenCV is a highly utilized open source computer vision library through which facial features can be recognized effectively. Polynomial kernel based support vector machine (SVM) is an advanced classification technique through which drowsiness can be classified from face. SVM is advanced machine learning approach through which linear and non-linear data can be classified with higher level of accuracy. System pertained 96.17 % of accuracy. Polynomial kernel is useful for non-linear data separation. Here system classifies the expressional features of face and result accordingly for drowsiness detection. Keywords: Support Vector Machine (SVM), OpenCV, Machine Learning, Non-Linear SVM Model, Drowsiness Detection, Face Detection, Computer Vision.

Sign in / Sign up

Export Citation Format

Share Document