RECOGNITION OF ACTIONS IN DAILY LIFE AND ITS PERFORMANCE ADJUSTMENT BASED ON SUPPORT VECTOR LEARNING

2004 ◽  
Vol 01 (04) ◽  
pp. 565-583 ◽  
Author(s):  
TAKETOSHI MORI ◽  
MASAMICHI SHIMOSAKA ◽  
TATSUYA HARADA ◽  
TOMOMASA SATO
Keyword(s):  
Intelligent Systems ◽  
Daily Life ◽  
Back Propagation ◽  
Kernel Functions ◽  
Support Vector ◽  
Human Knowledge ◽  
Back Propagation Algorithm ◽  
Recognition Method ◽  
Learning Capability ◽  
Robust Learning

This paper presents a recognition method for human actions in daily life. The system deals with actions related to regular human activity such as walking or lying down. The main features of the proposed method are: (i) simultaneous recognition, (ii) expressing lack of clarity in human recognition, (iii) defining similarities between two motions by utilizing kernel functions derived from expressions of actions based on human knowledge, (iv) robust learning capability based on support vector machine. Comparison with neural networks optimized by a back propagation algorithm and decision trees generated by C4.5 proves that the accuracy of recognition in the proposed method is superior to others. Recognizing actions in daily life robustly is expected to ensure smooth communication between humans and robots and to enhance support functionality in intelligent systems.

Abutment scour in clear-water and live-bed conditions by GMDH network

2013 ◽  
Vol 67 (5) ◽  
pp. 1121-1128 ◽  
Author(s):  
Mohammad Najafzadeh ◽  
Gholam-Abbas Barani ◽  
Masoud Reza Hessami Kermani
Keyword(s):  
Back Propagation ◽  
Support Vector ◽  
Group Method ◽  
Scour Depth ◽  
Back Propagation Algorithm ◽  
Clear Water ◽  
Sediment Size ◽  
Svm Model ◽  
Vector Machines ◽  
Abutment Scour

In the present study, the Group Method of Data Handling (GMDH) network has been utilized to predict abutments scour depth for both clear-water and live-bed conditions. The GMDH network was developed using a Back Propagation algorithm (BP). Input parameters that were considered as effective variables on abutment scour depth included properties of sediment size, geometry of bridge abutments, and properties of approaching flow. Training and testing performances of the GMDH network were carried out using dimensionless parameters that were collected from the literature. The testing results were compared with those obtained using the Support Vector Machines (SVM) model and the traditional equations. The GMDH network predicted the abutment scour depth with lower error (RMSE (root mean square error) = 0.29 and MAPE (mean absolute percentage of error) = 0.99) and higher (R = 0.98) accuracy than those performed using the SVM model and the traditional equations.

Continuous Learning Framework for Freeway Incident Detection

1998 ◽  
Vol 1644 (1) ◽  
pp. 124-131 ◽  
Author(s):  
Srinivas Peeta ◽  
Debjit Das
Keyword(s):  
Neural Network ◽  
Back Propagation ◽  
Superior Performance ◽  
Incident Detection ◽  
Neural Net ◽  
Continuous Learning ◽  
Back Propagation Algorithm ◽  
Learning Capability ◽  
Detection Algorithms ◽  
On Line

Existing freeway incident detection algorithms predominantly require extensive off-line training and calibration precluding transferability to new sites. Also, they are insensitive to demand and supply changes in the current site without recalibration. We propose two neural network-based approaches that incorporate an on-line learning capability, thereby ensuring transferability, and adaptability to changes at the current site. The least-squares technique and the error back propagation algorithm are used to develop on-line neural network-trained versions of the popular California algorithm and the more recent McMaster algorithm. Simulated data from the integrated traffic simulation model is used to analyze performance of the neural network-based versions of the California and McMaster algorithms over a broad spectrum of operational scenarios. The results illustrate the superior performance of the neural net implementations in terms of detection rate, false alarm rate, and time to detection. Of implications to current practice, they suggest that just introducing a continuous learning capability to commonly used detection algorithms in practice such as the California algorithm enhances their performance with time in service, allows transferability, and ensures adaptability to changes at the current site. An added advantage of this strategy is that existing traffic measures used (such as volume, occupancy, and so forth.) in those algorithms are sufficient, circumventing the need for new traffic measures, new threshold parameters, and variables that require subjective decisions.

scholarly journals Neuronic Convolution Model_Li-Yun Fu

2020 ◽  
Author(s):  
Li-Yun Fu
Keyword(s):  
Neuron Model ◽  
Back Propagation ◽  
Kernel Functions ◽  
Spatiotemporal Pattern ◽  
Information Representation ◽  
Back Propagation Algorithm ◽  
Multilayer Network ◽  
Artificial Neuron ◽  
Spatiotemporal Information ◽  
Pattern Processing

How to represent spatiotemporal information in an artificial neuron model has been a problem of longstanding interest in artificial intelligence. After a brief review of recent advances, Caianiello’s neuronic convolutional model is extended in this paper for spatiotemporal information representation. The kernel functions that correspond to the convolutional neuron’s receptive field profile can be described by neural wavelets. The convolutional neuron-based multilayer network and its back propagation algorithm are developed to perform spatiotemporal pattern processing. The results provide a natural framework for the discussion of spatiotemporal information representation in an artificial neural network

Hybrid Intelligent Systems for Medical Diagnosis

2010 ◽  
pp. 187-202 ◽  
Author(s):  
Rahul Kala ◽  
Anupam Shukla ◽  
Ritu Tiwari
Keyword(s):  
Medical Diagnosis ◽  
Intelligent Systems ◽  
Fuzzy Inference ◽  
Back Propagation ◽  
Medical Engineering ◽  
Back Propagation Algorithm ◽  
Hybrid Intelligent Systems ◽  
Neuro Fuzzy ◽  
Soft Computing Techniques ◽  
Inference Systems

In this chapter authors describe the application of various soft computing techniques in the field of medical diagnosis. They also explained new approaches being applied to the field of Bio-Medical Engineering as well as many new models being proposed, like Hybrid Systems and standard Back Propagation Algorithm for this purpose. These are Adaptive Neuro Fuzzy Inference Systems, Ensembles and Evolutionary Artificial Neural Networks.

scholarly journals Improvised Admissible Kernel Function for Support Vector Machines in Banach Space for Multiclass Data

2013 ◽  
Vol 11 (2) ◽  
pp. 2273-2278
Author(s):  
Sangeetha Rajendran ◽  
B. Kalpana
Keyword(s):  
Banach Space ◽  
Learning Theory ◽  
Intelligent Systems ◽  
Learning Algorithm ◽  
Kernel Functions ◽  
Learning Ability ◽  
Support Vector ◽  
Training Time ◽  
Vector Machines ◽  
Optimal Kernel

Classification based on supervised learning theory is one of the most significant tasks frequently accomplished by so-called Intelligent Systems. Contrary to the traditional classification techniques that are used to validate or contradict a predefined hypothesis, kernel based classifiers offer the possibility to frame new hypotheses using statistical learning theory (Sangeetha and Kalpana, 2010). Support Vector Machine (SVM) is a standard kernel based learning algorithm where it improves the learning ability through experience. It is highly accurate, robust and optimal kernel based classification technique that is well-suited to many real time applications. In this paper, kernel functions related to Hilbert space and Banach Space are explained. Here, the experimental results are carried out using benchmark multiclass datasets which are taken from UCI Machine Learning Repository and their performance are compared using various metrics like support vector, support vector percentage, training time and accuracy.

scholarly journals Dew Point Temperature Estimation: Application of Artificial Intelligence Model Integrated with Nature-Inspired Optimization Algorithms

Water ◽  
2019 ◽  
Vol 11 (4) ◽  
pp. 742 ◽  
Author(s):  
Sujay Naganna ◽  
Paresh Deka ◽  
Mohammad Ghorbani ◽  
Seyed Biazar ◽  
Nadhir Al-Ansari ◽  
...  
Keyword(s):  
Optimization Algorithms ◽  
Back Propagation ◽  
Absolute Error ◽  
Dew Point ◽  
Estimation Accuracy ◽  
Accurate Estimation ◽  
Support Vector ◽  
Back Propagation Algorithm ◽  
Point Temperature ◽  
Dew Point Temperature

Dew point temperature (DPT) is known to fluctuate in space and time regardless of the climatic zone considered. The accurate estimation of the DPT is highly significant for various applications of hydro and agro–climatological researches. The current research investigated the hybridization of a multilayer perceptron (MLP) neural network with nature-inspired optimization algorithms (i.e., gravitational search (GSA) and firefly (FFA)) to model the DPT of two climatically contrasted (humid and semi-arid) regions in India. Daily time scale measured weather information, such as wet bulb temperature (WBT), vapor pressure (VP), relative humidity (RH), and dew point temperature, was used to build the proposed predictive models. The efficiencies of the proposed hybrid MLP networks (MLP–FFA and MLP–GSA) were authenticated against standard MLP tuned by a Levenberg–Marquardt back-propagation algorithm, extreme learning machine (ELM), and support vector machine (SVM) models. Statistical evaluation metrics such as Nash Sutcliffe efficiency (NSE), root mean square error (RMSE), and mean absolute error (MAE) were used to validate the model efficiency. The proposed hybrid MLP models exhibited excellent estimation accuracy. The hybridization of MLP with nature-inspired optimization algorithms boosted the estimation accuracy that is clearly owing to the tuning robustness. In general, the applied methodology showed very convincing results for both inspected climate zones.

scholarly journals Neuronic Convolution Model_Li-Yun Fu

2020 ◽  
Author(s):  
Li-Yun Fu
Keyword(s):  
Neuron Model ◽  
Back Propagation ◽  
Kernel Functions ◽  
Spatiotemporal Pattern ◽  
Information Representation ◽  
Back Propagation Algorithm ◽  
Multilayer Network ◽  
Artificial Neuron ◽  
Spatiotemporal Information ◽  
Pattern Processing

How to represent spatiotemporal information in an artificial neuron model has been a problem of longstanding interest in artificial intelligence. After a brief review of recent advances, Caianiello’s neuronic convolutional model is extended in this paper for spatiotemporal information representation. The kernel functions that correspond to the convolutional neuron’s receptive field profile can be described by neural wavelets. The convolutional neuron-based multilayer network and its back propagation algorithm are developed to perform spatiotemporal pattern processing. The results provide a natural framework for the discussion of spatiotemporal information representation in an artificial neural network

scholarly journals PREDIKSI KUALITAS HASIL HUTAN LAHAN BASAH MENGGUNAKAN BACKPROPAGATION

2016 ◽  
Vol 1 (1) ◽  
pp. 34-42
Author(s):  
Husnul Khatimi ◽  
Yuslena Sari
Keyword(s):  
Intelligent Systems ◽  
Cocos Nucifera ◽  
Back Propagation ◽  
Texture Features ◽  
Back Propagation Algorithm ◽  
Histogram Method ◽  
Image Histogram ◽  
Backpropagation Method

Many forests are wetlands plant palm or tribe (family) Arecaceae. One type is the coconut (Cocos nucifera) is often utilized all its parts including stem used for wood materials, the process of selecting coconut wood are used as ingredients of a product made by a grader trained by observing the wood directly without using tools (manual). The method of causing dependence expertise and experience in the selection of a grader coconut wood. With the limitations of a grader, then arises a problem when a large number of coconut wood objects tested manually exceeds the capacity of a grader. Therefore, the grouping of coconut wood needs to be made with intelligent systems that can overcome these problems. Determination of coconut wood can be automatically built using backpropagation method to identify the parameters of the determining characteristics of coconut wood obtained from coconut wood image of two-dimensional (2D). Determination of coconut wood characteristic parameters based on the extraction of texture features based on the image histogram 2D coconut wood. Features texture obtained from the histogram method is among others: the mean intensity, standard deviation, skewness, energy, entropy, and subtlety. This paper describes the determination of the quality of coconut timber using back propagation algorithm based on coconut wood texture 2D image.

The Spinning Quality Control Management Based on Decision Making by Data Mining Techniques

2018 ◽  
Vol 7 (1) ◽  
pp. 72
Author(s):  
Khalid AA Abakar ◽  
Chongwen Yu
Keyword(s):  
Data Mining ◽  
Kernel Functions ◽  
Support Vector ◽  
Ann Model ◽  
Data Mining Techniques ◽  
Yarn Quality ◽  
Yarn Properties ◽  
Svm Model ◽  
Rbf Kernel

This work demonstrated the possibility of using the data mining techniques such as artificial neural networks (ANN) and support vector machine (SVM) based model to predict the quality of the spinning yarn parameters. Three different kernel functions were used as SVM kernel functions which are Polynomial and Radial Basis Function (RBF) and Pearson VII Function-based Universal Kernel (PUK) and ANN model were used as data mining techniques to predict yarn properties. In this paper, it was found that the SVM model based on Person VII kernel function (PUK) have the same performance in prediction of spinning yarn quality in comparison with SVM based RBF kernel. The comparison with the ANN model showed that the two SVM models give a better prediction performance than an ANN model.

Sign in / Sign up

Export Citation Format

Share Document