Nuryani

Electrocardiographic Signals and Swarm-Based Support Vector Machine for Hypoglycemia Detection

Cardiac arrhythmia relating to hypoglycemia is suggested as a cause of death in diabetic patients. This article introduces electrocardiographic (ECG) parameters for artificially induced hypoglycemia detection. In addition, a hybrid technique of swarm-based support vector machine (SVM) is introduced for hypoglycemia detection using the ECG parameters as inputs. In this technique, a particle swarm optimization (PSO) is proposed to optimize the SVM to detect hypoglycemia. In an experiment using medical data of patients with Type 1 diabetes, the introduced ECG parameters show significant contributions to the performance of the hypoglycemia detection and the proposed detection technique performs well in terms of sensitivity and specificity.

Premature ventricular contraction detection using swarm-based support vector machine and QRS wave features

A novel strategy for detecting Premature Ventricular Contraction (PVC) is proposed and investigated. The strategy employs a Swarm-based Support Vector Machine (SSVM). An SSVM is an SVM optimised by using Particle Swarm Optimisation (PSO). The strategy proposes new inputs. The inputs involve the width and the gradient of the electrocardiographic QRS wave. Experiments with different inputs and different SVM kernel functions are conducted to find the best one for PVC detection. On a test using clinical data, SSVM performs well in PVC detection with sensitivity, specificity and accuracy of 98.94%, 99.99% and 99.46%, respectively.

Automatic Detection of Atrial Fibrillation Using Basic Shannon Entropy of RR Interval Feature

Atrial Fibrillation is one of heart disease, that common characterized by irregularity heart beat. Atrial fibrillation leads to severe complications such as cardiac failure with the subsequent risk of a stroke. A method to detect atrial fibrillation is needed to prevent a risk of atrial fibrillation. This research uses data from physionet in atrial fibrillation database category. The performance of Shannon entropy has the highest accuracy if a threshold is 0.5 with accuracy 89.79%, sensitivity 91.04% and specificity 89.01%. Based on the result we get a conclusion, the ability of Shannon entropy to detect atrial fibrillation is good.

Studi pendahuluan biosensor berbasis magneto-impedansi

Bio-impedansi sensor mulltilayer [NiFe(800)/Cu(300)] 4 telah berhasil dibuat dengan metode elektro-deposisi. Respon bio-magneto-impedansi didefinisikan sebagai perubahan impedansi akibat medan terpasang (MI) dengan dan tanpa sampel daging. Profil respon bio-MI sampel daging sapi memiliki bentuk kurva yang setipe dengan kurva rasio magneto-impedansi dan bergantung pada frekuensi pengukuran. Respon bio-MI padapenelitian ini terbesar 0,7% pada frekuensi 100 kHz.

Demonstration of Magneto-Impedance Sensor on Multilayer Coil [Ni80Fe20/Cu]N Result of Electro-Deposition

Demonstration performance magneto - impedance sensor on the coil wire multilayer [ Ni80Fe20/Cu ]N electro - deposition results presented in this paper . At first multilayer [ Ni80Fe20/Cu ]N deposited on a Cu wire into a coil and then the sample is modified by the number of windings 2 and 4. The results of impedance measurements under the influence of the magnetic field shows that the magneto - impedance ratio increases with the increase in the number of windings. Magneto - impedance ratio changed from 15 % to 17.4% with a change in the number of windings of 2 to 4. The fact these results allegedly contributed their self-inductance value of this magnitude greater contribution to the increase in the number of windings. Keywords: Magneto - impedance sensor, electro-deposition , multilayer coils [Ni80Fe20/Cu]N

Pembuatan Elektrokardiogram dan Penentuan Interval QRS secara Otomatis

Pada penelitian ini telah dibuat rancangan sistem elektrokardiogram (EKG) yang dilengkapi dengan sistem penentuan interval QRS secara otomatis. Sistem EKG yang dibuat menggunakan arduino dan komputer. Hasil dari penelitian ini diimplementasikan menggunakan perangkat lunak processing. Data sinyal jantung yang digunakan pada penelitian ini diambil langsug dari pasien. Untuk menentukan interval QRS maka terlebih dahulu dilakukan penentuan posisi puncak R. Posisi puncak R selanjutnya digunakan untuk menentukan posisi titik Q dan posisi titik S. Hasil akurasi penentuan interval QRS pada penelitian ini adalah sebesar 95,89%. ABSTRACT In this research, system design electrocardiogram (EKG) that is equipped with a QRS interval determination system automatically. ECG systems created using arduino and computer. The results of this research are implemented using software processing. Cardiac signal data used in this research were taken of patients. To determine the QRS interval, the first is the determination of the peak position R. Peak position R is then used to determine the position of the point Q and the position of the point S. Result for accuracy determination QRS interval in this research amounted to 95.89%.

Detection of Atrial Fibrillation Using Artifical Neural Network with Power Spectrum Density of RR Interval of Electrocardiogram

Atrial fibrillation (AF) is a disorder of the heart with fairly high mortality in adults. AF is a common heart arrythmia which is characterized by a missing or irregular contraction of atria. Therefore, finding a method to detect atrial fibrillation is necessary. In this article a system to detect atrial fibrillation has been proposed. Detection system utilized backpropagation artifical neural network. Data input in this method includes power spectrum density of R-peaks interval of electrocardiogram which is selected by wrapping method. This research uses parameter learning rate, momentum, epoch and hidden layer. System produces good performance with accuracy, sensitivity, and specificity of 83.55%, 86.72 % and 81.47 %, respectively.

Atrial fibrillation detection using support vector machine and electrocardiographic descriptive statistics

This paper proposes a new technique for detecting atrial fibrillation (AF). The method employs electrocardiographic features and support vector machine (SVM). The features include descriptive statistics of electrocardiographic RR interval. The RR interval is the distance in time between two consecutive R-peaks of electrocardiogram. AF detections using SVM with different electrocardiographic features and different SVM free parameters are explored. Employing SVM with the optimal free parameters and all the proposed electrocardiographic features, we find an AF detection technique with a comparable performance. The best performance obtained by the technique is 98.47% and 97.84%, in terms of sensitivity and specificity.

Critical diameter and magneto-impedance effect in electrodeposited [Cu/Ni80Fe20]3 multilayer wire at low frequency

The effects of the copper wire diameter deposited with multilayer [Cu/Ni80Fe20]3 to its magneto-impedance ratio have been observed. The observation is conducted at low frequencies (20 – 100 kHz) with variations of copper wire diameter from 0.1 to 1 mm. The results show that the maximum magneto-impedance ratio is achieved at the wire diameter of 0.5 mm which is equal to 54.6% / Oe. At the wire diameter of less than 0.5 mm, the magneto-impedance ratio increases with the increasing diameter. While the magneto-impedance ratio decreases with the increasing diameter at the wire diameter of more than 0.5 mm. Studies on the influences of diameter is an important part to optimize the manufacture of magnetic sensor based on magneto-impedance effect on the wire.

Detection of atrial fibrillation using coherency of power spectrum in electrocardiogram

Atrial fibrillation (AF) is a disorder of the heart with fairly high mortality in adults. AF is a common heart arrythmia which is characterized by a missing or irregular contraction of atria.This article uses the method of power spectrum coherence as one of the characteristics of a signal used to detect atrial fibrillation atrium on electrocardiograph. This research was able to detect AF signal based on the coherence of the power spectrum. This method produces performance with accuracy, sensitivity, and specifications that is 63.98%, 65.02% and 63.55% respectively.