Ram Pal Singh

A novel image watermarking scheme using Extreme Learning Machine

In this paper, a novel digital image watermarking algorithm based on a fast neural network known as Extreme Learning Machine (ELM) for two grayscale images is proposed. The ELM algorithm is very fast and completes its training in milliseconds unlike its other counterparts such as BPN. The proposed watermarking algorithm trains the ELM by using low frequency coefficients of the grayscale host image in transform domain. The trained ELM produces a sequence of 1024 real numbers, normalized as per N(0, 1) as an output. This sequence is used as watermark to be embedded within the host image using Coxs formula to obtain the signed image. The visual quality of the signed images is evaluated by PSNR. High PSNR values indicate that the quality of signed images is quite good. The computed high value of SIM (X, X*) establishes that the extraction process is quite successful and overall the algorithm finds good practical applications, especially in situations that warrant meeting time constraints.

Digital Image Watermarking in DCT Domain Using Finite Newton Support Vector Regression

Finite Newton Support Vector Regression (FNSVR) is a reliable and robust method for regression analysis which unlike other support vector regression methods, converges the computation in a few iterations. In this paper, we have used FNSVR method for embedding and extracting a binary image as a watermark in 8-bit gray scale cover images. Digital image watermarking being a time consuming task, requires fast embedding and extraction procedures and overall it should have a low time complexity. FNSVR being an algorithm which consumes less number of iterations, embeds a given watermark in a short time span. Computed PSNR values indicate good quality of the signed images. parameter is computed and its values indicate that the extraction process is quite successful.

On finite Newton method for support vector regression

In this paper, we propose a Newton iterative method of solution for solving an ε-insensitive support vector regression formulated as an unconstrained optimization problem. The proposed method has the advantage that the solution is obtained by solving a system of linear equations at a finite number of times rather than solving a quadratic optimization problem. For the case of linear or kernel support vector regression, the finite termination of the Newton method has been proved. Experiments were performed on IBM, Google, Citigroup and Sunspot time series. The proposed method converges in at most six iterations. The results are compared with that of the standard, least squares and smooth support vector regression methods and of the exact solutions clearly demonstrate the effectiveness of the proposed method.

Intelligent Energy Conservation: Indoor Temperature Forecasting with Extreme Learning Machine

At present, most of the buildings are using process of heating, ventilation and air conditioning (HVAC)-systems. HVAC systems are also responsible for consumption of huge amount of energy. Home automation techniques are being used to reduce the waste of resources especially energy that is available to us in the form of temperature, electricity, water, sunlight, etc. Forecasting and predicting the future demand of the energy can help us to maintain and to reduce the cost of energy in the buildings. In this paper, we use the experiments the small medium large system (SML system) which is the house built at the university of CEU cardinal Herrera (CEU-UCH) for competition named Solar Decathlon 2013. With the data available from this experiments, we try to predict and forecast the future temperature condition intelligently for energy conservation with the model based on Extreme Learning Machine (ELM). This will help in determining the energy needs of the buildings and further will help in efficient utilization and conservation of energy.

Online Sequential Extreme Learning Machine for watermarking in DWT domain

Protecting and securing an information of digital media is very crucial due to illegal reproduction and modification of media has become an acute problem for copyright protection now a day. A Discrete Wavelet Transform (DWT) domain based robust watermarking scheme with Extreme Learning Machine (ELM), Online Sequential Extreme Learning Machine (OSELM) and Weighted Extreme Learning Machine (WELM) have been implemented on different color images. The proposed scheme which combine DWT with ELM, OSELM and WELM machine learning methods and a watermark or a tag or a sequence is embedded as an ownership information. Experimental results demonstrate that the proposed watermarking scheme is imperceptible/transparent and robust against image processing and attacks such as blurring, cropping, JPEG, noise addition, rotation, scaling, scaling-cropping, and sharpening. Performance and efficacy of algorithms of watermarking scheme is determined by measuring Peak Signal to Noise Ratio (PSNR), Bit Error Rate (BER) and Similarity parameter SIM ( X , X * ) and calibrated results are compared with other existing machine learning methods. As a watermark detector, machine learning techniques are used to learn neighbors relationship among pixels in a natural image has high relevance to its neighbors, so this relationship can be predicted by its neighbors using machine learning methods and watermark image can be extracted and detected and thereby ownership can be verified.

On Extreme Learning Machine for Watermarking of an Images in Discrete Wavelet Transform Domain

In this paper, an implementation and efficacy of Extreme Learning Machine (ELM) algorithm for watermarking of an images in Discrete Wavelet Transform (DWT) domain has been demonstrated. ELM is a regularization algorithm works based on the concept of generalized single-hidden-layer feed forward neural networks (SLFNs) with different activation functions likes rbf, sine, sigmoid and hardlim in hidden nodes in unified environment framework. In this learning method, the parameters of hidden nodes like the input weight and bias value of additive nodes are randomly selected based on input data samples. This algorithm developed for batch learning is extremely good and has better generalization performance. Except from selecting the number of hidden nodes, no other learning parameter is selected here manually. Detail performance and efficacy of this algorithm is tested on watermarking purpose on color images in Discrete Wavelet Transform (DWT) domain. The results show that watermarking scheme based on ELM is very robust and imperceptible and produces better generalization performance against common image processing attacks.

ELM variants comparison on applications of time series data forecasting

Extreme learning machine (ELM) which belongs to randomized algorithm categories, is versatile and an emerging learning algorithm. ELM has been developed for different application starting from pattern recognition, function estimation, regression analysis, time series analysis, and big data analysis etc. Unlike feed forward neural networks where slow convergence rate, imprecise learning parameters, presence of local minima are major bottles neck, This paper addresses these problems using different variants of ELM on some bench mark time series data. ELM and its variants where hidden nodes parameters like weights and biases are randomly generated and fixed during the time of learning process, also give results of weights as an output of single hidden layer feed forward neural networks (SLFNs) analytically. The paper performs experiments on two time series data and demonstrates that variants of ELM delivers good performance in generalized manner in several cases without compromising on accuracy.

Machine Learning-Based Method and Its Performance Analysis for Occupancy Detection in Indoor Environment.

Occupancy detection is very interesting research problem which may help in understanding ambient dynamics of the environment, resource utilisation, energy conservation and consumption, electricity usages and patterns, security and privacy related aspects. In addition to this, achieving good accuracy for occupancy detection problem in the home and commercial buildings can help in cost reduction substantially. In this paper, we explain one experiment in which data for occupancy and ambient attributes have been collected. This paper develops machine learning-based intelligent occupancy detection model and compare the results with several machine learning techniques in a detailed manner.

Weighted Extreme Learning Machine for Digital Watermarking in DWT Domain

In this paper, a digital watermarking scheme has been implemented using Weighted Extreme Learning Machine (WELM) on images and results are compared with other existing methods. The neighbourhood relationship among the pixel in image can be used as an reference positions, WELM is used as a regressor. Digital watermarking problem can be treated as regression problem can be trained at the embedding procedure and watermark or logo or sequence can be embedded. The watermark as an information can be embedded into blue channel of input images used for watermarking taking into account of human vision system (HSV). As WELM algorithm is very fast, cost sensitive and has good learning and generalization ability, the watermark can be correctly extracted despite of the watermarked image subject to several malicious attacks. Experimental results show that the WELM based watermarking scheme outperformed other existing methods against different attacks including salt & peppers (0:04), scaling 50%, cropping 15%, rotation 150 etc. As implemented digital watermarking scheme is robust and imperceptible determined based on calculated metrics PSNR, BER.

Financial Time Series Forecasting Using Deep Learning Network

The analysis of financial time series for predicting the future developments is a challenging problem since past decades. A forecasting technique based upon the machine learning paradigm and deep learning network namely Extreme Learning Machine with Auto-encoder (ELM-AE) has been proposed. The efficacy and effectiveness of ELM-AE has been compared with few existing forecasting methods like Generalized Autoregressive Conditional Heteroskedastcity (GARCH), General Regression Neural Network (GRNN), Multiple Layer Perceptron (MLP), Random Forest (RF) and Group Method of Data Handling (GRDH). Experimental results have been computed on two different time series data that is Gold Price and Crude Oil Price. The results indicate that the implemented model outperforms existing models in terms of qualitative parameters such as mean square error (MSE).