Many medical reports and documents in printed form are available in huge sizes in archive units inside medical centers and hospitals around the world. The printed electrocardiogram paper is one type of archive data and is more powerful for expert cardiologists to study various cardiac diseases. On the other hand, the widespread development in the ability of intelligent computer systems to process digital signals increases the benefit of these data if converted to digital form. In this paper, a new approach for digital recovery of 12-lead electrocardiogram raw data from the printed colored scanned image has been proposed. This approach implements an algorithm with four steps including delineating effective regions, color filtering, contacting detected points, and sampling the resulted digital signals to reconstruct the digital electrocardiogram signal from the printed drawing of the same signal after digital scanning with significant resolution. Also, this algorithm is designed to process various kinds of printed electrocardiogram papers. The performance of the proposed approach is evaluated qualitatively by visual inspection of the recovered and original signals in the same graph. Also, the similarity of these signals is evaluated quantitatively using some standard evaluation metrics. The simulation results show the consistency and robustness of the proposed digital recovery approach to generate electrocardiogram digital data with a high percentage accuracy exceeding 98%. Also, plotting the recovered signal with the original printed signal on the same graph shows a significant percentage of congruence in time and amplitude. Finally, the proposed idea in this study opens the way for an unlimited bank of digital electrocardiogram data with different morphologies.

In the past few years, physical therapy plays a crucial role during rehabilitation. Numerous efforts are made to demonstrate the effectiveness of medical/ clinical and human-machine interface (HMI) applications. One of the most common control methods is using electromyography (EMG) signals generated by muscle contractions to implement the prosthetic human body parts. This paper presents an EMG signal classification system based on the EMG signal. The data is collected from biceps and triceps muscles for six different motions, i.e., bowing, clapping, handshaking, hugging, jumping, and running using a Myo armband with eight electromyography sensors. The Root Mean Square, Difference Absolute Standard Deviation Value, and Principle Component Analysis are used to extract the raw signal data and enhance classification accuracy. The machine learning method is applied, i.e., Support Vector Machine and K-Nearest Neighbors are used for classification; the results show that the K-Nearest Neighbors method achieves a higher accuracy percentage than the SVM. Making high training accuracy for different physical actions helps implement human prosthetic parts to help the people who suffer from an amputee.

The revolution in prosthetic hands allows the evolution of a new generation of prostheses that increase artificial intelligence to control an adept hand. A suitable gripping and grasping action for different shapes of the objects is currently a challenging task of prosthetic hand design. The most artificial hands are based on electromyography signals. A novel approach has been proposed in this work using deep learning classification method for assorting items into seven gripping patterns based on EMG and image recognition. Hence, this approach conducting two scenarios; The first scenario is recording the EMG signals for five healthy participants for the basic hand movement (cylindrical, tip, spherical, lateral, palmar, and hook). Then three time-domain (standard deviation, mean absolute value, and the principal component analysis) are used to extract the EMG signal features. After that, the SVM is used to find the proper classes and achieve an accuracy that reaches 89%. The second scenario is collecting the 723 RGB images for 24 items and sorting them into seven classes, i.e., cylindrical, tip, spherical, lateral, palmar, hook, and full hand. The GoogLeNet algorithm is used for training based on 144 layers; these layers include the convolutional layers, ReLU activation layers, max-pooling layers, drop-out layers, and a softmax layer. The GoogLeNet achieves high training accuracy reaches 99%. Finally, the system is tested, and the experiments showed that the proposed visual hand based on the myoelectric control method (Vision-EMG) could significantly give recognition accuracy reaches 95%.

The noise within an electrocardiogram signal can cause errors that are viewed in the results of different ECG characteristics, in both amplitude and time interval which ultimately lead to a incorrect diagnosis of cardiac disease. In this paper, a new approach of de-noising the electrocardiogram signal is proposed using multi-iteration of the moving average filter. The algorithm of the proposed approach includes two main steps: first to estimate the amount of noise presents in the ECG signal, second to remove the noise added. The proposed de-noising approach is validated with ECG records which were collected from the MIT-BIH ECG database with different amounts of additive gauss white noise. The validation results prove the robustness of proposed de-noising approach to provide the greatest signal to noise ratio improvement, and to give a reduction of 50% or more in terms of standard metrics used for computing distortion in a noisy signal. Additionally, the filtered signal has a smooth shape in comparison with the adopted de-noising ECG signal techniques.

In this paper a robust approach for detecting QRS complexes and computing related R-R intervals of ECG signals named (RDQR) has been proposed. It reliably recognizes QRS complexes based on the deflection occurred between R & S waves as a large positive and negative amplitude differences in comparison with respect to other ECG signal (P and T) waves. The proposed detection approach applies the new direct algorithm applied on the entire ECG itself without any additional transform like (wavelet, cosine, Walsh transform, etc.). According to the strategy based on positive and negative deflection it overcomes the problem of QRS direction positive (upright) or negative (inverted). Three different types of ECG online database with duration of 10 sec (MIT-BIH Arrhythmia, ST Change Database and Normal Sinus Rhythm) are used to validate the detection performance. The results are demonstrated that the proposed detection approach achieved (100%) accuracy for QRS detection also very high accuracy in evaluating related R-R intervals.

This study presents a new fuzzy inference system for diagnosing left ventricular hypertrophy cardiac disease based on the proposed diagnostic criterion. In contrast to the conventional diagnostic criteria, the main decision of proposed criterion includes three logical expressions. Two of them are determined by a combination of classic criteria, whereas the third expression is obtained directly using eight voltages of the electrocardiogram leads and takes two different levels for each gender. All expressions are represented by the membership functions in a fuzzy inference system. The proposed diagnostic approach is validated by 34 records from St Petersburg INCART 12-Lead Arrhythmia Database and 16 reconstructed records from the printed chart diagram using digital data recovery. The total validated samples include 21 data with left ventricular hypertrophy and 29 data with other cardiac diseases and some normal samples. The simulation results prove that the proposed system performs perfect sensitivity, specificity, and accuracy of diagnosing left ventricular hypertrophy.

Identifying and delineating P and T wave characteristics are greatly important in interpreting and diagnosing electrocardiogram (ECG) signals. P and T waves with high accuracy are more difficult to delineate because of their various shapes, positions, directions and boundaries. This paper proposes a high-speed approach to delineate P and T waves in a single lead using two high-speed algorithms of high detection accuracy. This approach presents a simple, adaptive and intelligent P and T wave scan method that determines the onset, peak and end time locations within an adaptive period appointed by previous records of the QRS complex. By using a translating (rising to/from falling) interval inside the scan wave, the peak time location of P and T waves and the T wave sign (upward or downward) are determined. Continuously, this time location is considered a reference point for determining the onset and the end time locations based on a series of computed outcomes related to amplitude and slope difference. The new approach is validated by 105 annotated records from the QT database collected from seven different categories of ECG signals. Simulation results show that the average detection rates of sensitivity and positive predictivity are equal to 99.97% and 99.36% for P wave and 99.98% and 99.26% for T wave, respectively. The average time errors computed by the mean and standard deviation for the P wave onset, peak and end time locations are -3.00 ± 2.94, -0.69 ± 4.42 and 0.67 ± 4.56 ms, respectively. The values for T wave are -3.33 ± 4.96, 0.24 ± 5.36 and -0.36 ± 5.68 ms. Results demonstrate the reliability, accuracy and forcefulness of the proposed approach in delineating various categories of P and T waves.

In this paper, four levels of analysis and synthesi s filter banks are proposed to create, coefficients for a continuous wavelet transform (CWT), a discrete wavelet transform (DWT), and an inverse, discrete wavel et transform (IDWT). The main property of these wavelet transform schemes is their ability to construct t he transmitted signal across a log-normal fading chann el over additive, white Gaussian noise (AWGN). There are many applications of wavelet transforms in wire less communication systems, and we chose the design of rake receivers as a major application to mitigat e interferences and reduce the noise. In this resea rch, a new scheme of rake receivers was proposed to receive indoor, multi-path components (MPCs) for ultrawideband (UWB) wireless communication systems. Rake receivers consist of a continuous wavelet rake (CWR) and a discrete wavelet rake (DWR), and they use huge bandwidth (7.5 GHz), as reported by the Federal Communications Commission (FCC). The indoor channel models chosen for analysis in this research were the line-of-sight (LOS) channel model (CM1 from 0 to 4 meters) and the non-line-of-sight (NLOS) channel model (CM3 from 4 to 10 meters). Two types of rake receiver were used in the simulation , i.e., partial-rake and selective-rake receivers wit h the maximal ratio combining (MRC) technique to capture the energy of the signal from the output of the rak e’s fingers. In the simulation, the transmitted and received radiations are presented with UWB single-in, single -out (SISO) with Walsh matrix coding.

The extracted features from the QRS complex in the electrocardiogram (ECG) signal are considered mainly in the heart rate evaluation and cardiac disease diagnosis. In this paper, high speed approach named “Rising Falling Transition Method (RFTM)” is proposed to detect the characteristics of QRS complex in single lead ECG signal. The proposed approach applies single straight forward algorithm with two stages. The first stage takes the advantage of the transition from rising to falling edge inside each QRS complex as a base to determine the time locations of the vertices in a triangle that composes from the Q-wave end, R-wave peak, and S-wave onset. The second stage determines the time location of Q-wave onset and S-wave end (J-point) using a linear scan along short period which starts from Q-wave end and S-wave onset towards the target end points at Q-wave onset and S-wave end, respectively. The detector approach is able to detect QRS complex of different morphologies (wide/small interval, high/low amplitude, and negative polarities). The detection performance of the proposed approach is evaluated on a single channel of some annotated records from the QT database which collected from seven ECG categories and 48 annotated records from MIT-BIH database. Simulation results show that the average detection rates of sensitivity (Se) and specificity (Sp) are 99.84% and 99.94%, respectively for MIT-BIH Arrhythmia database. The validation results prove the reliability and accuracy of proposed RFTM approach.

The extracted features from the QRS complex in the electrocardiogram (ECG) signal are considered mainly in the heart rate evaluation and cardiac disease diagnosis. In this paper, high speed approach named "Rising Falling Transition Method (RFTM)" is proposed to detect the characteristics of QRS complex in single lead ECG signal. The proposed approach applies single straight forward algorithm with two stages. The first stage takes the advantage of the transition from rising to falling edge inside each QRS complex as a base to determine the time locations of the vertices in a triangle that composes from the Q-wave end, R-wave peak, and S-wave onset. The second stage determines the time location of Q-wave onset and S-wave end (J-point) using a linear scan along short period which starts from Q-wave end and S-wave onset towards the target end points at Q-wave onset and S-wave end, respectively. The detector approach is able to detect QRS complex of different morphologies (wide/small interval, high/low amplitude, and negative polarities). The detection performance of the proposed approach is evaluated on a single channel of some annotated records from the QT database which collected from seven ECG categories and 48 annotated records from MIT-BIH database. Simulation results show that the average detection rates of sensitivity (Se) and specificity (Sp) are 99.84% and 99.94%, respectively for MIT-BIH Arrhythmia database. The validation results prove the reliability and accuracy of proposed RFTM approach.

Electricity generated by solar energy has been widely applied worldwide; there is a great tendency for the use of stand-alone photovoltaic stations distributed in remote areas due to the known benefits of this source of energy. In Iraq there are other reasons why the use of solar energy so necessary, firstly, appropriate climatic conditions, secondly, delayed electricity supply projects for remote areas.This paper presents the development of a visual basic-based software package that design a standalone photovoltaic system, the developed software offers a friendly Graphic User Interface tool to size the system components according to the load requirements and site-specification. The results of the design for the case study are quite in agreement with the analytical method, thus validating the accuracy and precision of the tool.The final outcome of this paper is to prepare a design tool that can be used by those who do not have any engineering or technical background which helps to accept the idea of using solar energy by residents of remote areas. (C) 2013 The Authors. Published by Elsevier Ltd. Open access under CC BY-NC-ND license. Selection and/or peer-review under responsibility of the TerraGreen Academy

In this study, an automatic approach for detecting QRS complexes and evaluating related R-R intervals of ECG signals (PNDM) is proposed. It reliably recognizes QRS complexes based on the deflection occurred between R & S waves as a large positive and negative interval with respect to other ECG signal waves. The proposed detection method follows new fast direct algorithm applied to the entire ECG record itself without additional transformation like discrete wavelet transform (DWT) or any filtering sequence. Mostly used records in the online ECG database (MIT-BIH Arrhythmia) have been used to evaluate the new technique. Moreover it was compared to seven existing techniques; the results show that PNDM has much detection performances according to 99.95% sensitivity and 99.97% specificity. It is also quickest than comparable methods.