Hand gesture recognition provides a significant impact in the field of human–computer interaction. It introduces the information, tools, and systematic design techniques, by which accuracy and easy implementation of daily tasks can be achieved. Gesture recognition is the approach by which computers can detect hand gestures. Human–computer interaction provides appropriateness in feedback, effortless implementation, and timely completion of the goal. Computer vision plays an important role in extracting high levels of comprehension from electronic images and videos. It is applied to a hand gesture recognition system to provide input to the computer to manipulate virtual objects by simply moving hand parts which act as a command. Providing a low-cost infrastructure device that alters the need for keyboards and mouse in laptops and computers.

This paper illustrates the cloud-based telemonitoring framework that implements healthcare automation system for myocardial infarction (MI) disease classification. For this purpose, the pathological feature of ECG signal such as elevated ST segment, inverted T wave, and pathological Q wave are extracted, and MI disease is detected by the rule-based rough set classifier. The information system involves pathological feature as an attribute and decision class. The degree of attributes dependency finds a smaller set of attributes and predicted the comprehensive decision rules. For MI decision, the ECG signal is shared with the respective cardiologist who analyses and prescribes the required medication to the first-aid professional through the cloud. The first-aid professional is notified accordingly to attend the patient immediately. To avoid the identity crisis, ECG signal is being watermarked and uploaded to the cloud in a compressed form. The proposed system reduces both data storage space and transmission bandwidth which facilitates accessibility to quality care in much reduced cost.

In this study, a computerized diagnosis system is developed using Rough set classifier from multi-lead ECG signal for detection as well as the classification of five different types of myocardial infarction (MI) disease. The pathological features of ECG such as Inverted T-wave, ST segment deviation, or pathological Q wave, which are seen during MI, are extracted. An Information table and the knowledgebase are expanded from these pathological features after getting feedback from the cardiologist as well as consulting different medical books. The Information table contains 36 features and 341objects which include normal and five types of MI such as Anterior (AN), Inferior (IN), Antero lateral (ANLA), Inferior lateral (INLA), and Antero septal (ANSE) are used for assessment. The proposed system determines the degree of attributes dependency and their significance to find a smaller set of attributes, called reduct, alike the original set to predict the appropriate decision rules for MI classification. The robustness is justified by the "five-fold cross" validation technique using RSES tools. Finally, the proposed classifier illustrates its outperformance over the existing approaches in terms of sensitivity (99.75%), and accuracy (99.8%) for MI detection and 99.8% accuracy for MI classification.

This paper describes the rough set classifier for cardiac disease classification over the medical dataset obtained from characteristics feature of ECG signals. The sets of characterizes feature are used as an information system to find minimal decision rules that may be used to identify one or more diagnostic classes. After gathering knowledge from various medical books as well as feedback from well-known cardiologists, a knowledge base has been developed. The rough set-based degree of attributes dependency technique and their significance predicted the universal least decision rules. Such rule has the least number of attributes so that their combination defines the largest subset of a universal decision class. Hence, the minimal rule of an information system is adequate for predicting probable complications. Lastly, the performance parameters such as accuracy and sensitivity have been expressed in the form of confusion matrix by ROSETTA software which yields information about actual and predicted classification achieved by the proposed system.

A very simple and novel idea based on adaptive window dependent differential histogram approach has been proposed for automatic detection and identification of ECG waves with its characteristic features. To facilitate the estimation of the waves, the normalised signal has been divided into a few small windows by an adaptive window selection technique. By counting the number of changes between successive samples as frequency, the differential histogram has been plotted. Some of the zones having an area more than a pre-defined threshold are depicted as QRS zones. The local maxima of these zones are referred as the R-peaks. T and P peaks are also detected. Baseline point and clinically significant time plane features have been computed and validated with reference values of the CSE database. The proposed technique achieved better performance in comparison with CSE groups. Its accuracy is achieved in sensitivity (99.86%), positive productivity (99.76%) and detection accuracy (99.8%).

A histogram based simple and novel idea is proposed here for detection and identification of R wave, P wave and T wave from noise removal ECG Signal. The identification of ECG waveforms and their characteristic features is an important task for the diagnosis. In this work, histograms, a graphical demonstration of numerical data of equal size, is used as an estimator of the above mentioned waves of ECG signal. For this purpose the whole signal is divided into few small windows of predefined width having maximum 60 sample values in each. The Histograms are basically generated by measuring the variations of the orientations among these sample values in some quantized directions. After getting the histograms, few zones are depicted as QRS zones having the area more than a pre-defined threshold. The local maxima of these zones are considered as the R-peak. Based on same technique, P and T wave can also be detected. The method is advantageous as it can be used directly for online analysis without using any complex mathematical models. The whole technique has been established to be useful to a variety of ECG records for all the 12 leads taken from CSE Multi-lead ECG database which contains 5000 samples recorded at a sampling frequency of 500Hz. The algorithm is implemented on MATLAB R2010a environment. The performance of the proposed technique is evaluated. The accuracy of the proposed technique is achieved in Sensitivity (Se=99.86%), Positive Predictivity (+p=99.76%) and Detection accuracy (DA 99.8%) and hence we conclude that the proposed technique may be used for ECG analysis and classification.

In Telemedicine applications, Digital watermarking is a technique to improve the security and authenticity of ECG signals transmitted to the doctor's end through GSM network. Keeping this in mind, the authors of this paper propose a new watermarking technique which embeds patient's identification inside the ECG signals that will enhance the security and authenticity of ECG signals. In this paper ECG signals are watermarked with patient identity using Adaptive Normalization Factor (ANF) and Least Significant Bit (LSB) watermarking technique to avoid confusion between the ECG signals and patient's identity. The entire technique has been found to be useful to a variety of ECG records for all the 12 leads taken from CSE Multi-lead ECG diagnostic record and the maximum 15 character string that is used to implant watermark embodies for patient's recognition. The novelty of the projected watermarking technique is that the implanted watermark can be completely detached from any altered form of actual signal. It has been observed that the projected method gives a marginal quantity of signal distortion (0.018%), which does not have an effect on any vital features of the ECG signals and it also does not cause any changes in the diagnosis.

In the application of telemedicine, ECG signal is transmitted to the Doctor end without any patient details. As a result, confusion is arisen between signal and patient’s identity. To avoid this confusion, ECG signals need to be combined with patient confidential information when sent. A typical ECG monitoring device generates massive volumes of digital data. Huge amount of bandwidth is required for the transmission of the ECG signal for telemedicine purposes. This huge amount of bandwidth for the transmission of the ECG signal can be avoided if the signal is compressed after embedding the patient’s personal information within the ECG signal. Since the ECG signal and the patient details integrated into one, bandwidth for the transmission can be reduced in telemedicine applications. In this paper ECG signals are watermarked with patient information using LSB watermark technique and compressed the huge amount of ECG data using ASCII character encoding in order to confirm patient or ECG linkage integrity and reduced the bandwidth in telemedicine applications. The whole module has been applied to various ECG data of all the 12 leads taken from PTB diagnostic database (PTB-DB) of physioNet and gives a highly compressed result that can be stored using far less digital space without distorting important ECG characteristics and at the same time, embedded information can be completely retrieved. Keywords— telemedicine, watermarked, ASCII character, PRD, SD, CR

In this paper, the authors propose a new ECG compression algorithm which embeds patient's identification inside the ECG data. The compressed file contains only ASCII characters. The proposed scheme also allows the decompression technique where the original ECG waveform can be exactly reconstructed and retrieve patient's identification from the ECG signal. The whole module has been applied to various ECG data of all the 12 leads taken from PTB diagnostic database (PTB-DB) of physioNet (www.physionet.org) and gives a highly compressed result that can be stored using far less digital space without distorting important ECG characteristics which are essential for proper medical diagnosis. Moreover, the compression, embedding, decompression and retrieving of data are achieved in a series of sequential, simplistic logical processes that can be easily executed. It is observed that the proposed algorithm gives a high compression ratio (CR=7.3593, an excellent Quality Score (QS=1362) and very low difference between original and reconstructed ECG signal (PRD=O.0054).