SHANIBA ASMI P - Academia.edu (original) (raw)

Papers by SHANIBA ASMI P

INTERNATIONAL JOURNAL OF RECENT TRENDS IN ENGINEERING & RESEARCH, Jun 30, 2019

Pregnancy monitoring is the most important challenge during gestation period. Some early deliveri... more Pregnancy monitoring is the most important challenge during gestation period. Some early deliveries cause mortality and morbidity of the new born babies. Electrohysterogram is the most promising method for monitoring the uterine contraction thus the physiological wellbeing of the foetal and the mother. As it is a non-invasive method there are no side effects and its accuracy for early diagnosis is more. There are different numbers of electrodes used to collect the signals from the mother's abdomen by placing electrodes on the abdomen. Through this paper we are focusing on different researches used for pregnancy monitoring using 16 electrode database. Based on the studies this paper provides different steps in electrohysterogram data processing such as preprocessing, feature extraction, classifiers for classifying pregnancy and labour contraction.

IETE Journal of Research, 2017

ABSTRACT One of the most interesting topics in the field of rehabilitation is that of upper-limb ... more ABSTRACT One of the most interesting topics in the field of rehabilitation is that of upper-limb myoelectric prosthetic control. It is a technique by which prostheses are controlled by means of surface electromyogram (sEMG) signals collected from remnant muscle tissues at the residual limb of an amputee. Intuitive control of multifunctional upper-limb prosthesis can be accomplished using pattern recognition (PR) of sEMG signals. In spite of the tremendous progress made in the research of the so-called mind-controlled artificial arm, none of the academic achievements has yet reached the end users. This review paper portrays the current state-of-the-art approach in sEMG pattern classification-based control, identifies the factors that hinder the clinical usability of the system and focuses on the recent research directions toward translating the academic findings into a commercially acceptable robust myoelectric prosthesis. Control strategies proposed for simultaneous and proportional control (SPC) of multiple degrees of freedom (DoFs), which is identified as the most significant barrier for the transition from laboratory to clinical practice, are discussed. Directions for future research are also briefly outlined.

IETE Journal of Research, 2019

ABSTRACTEarly detection of preterm labor is important to avoid neonatal death and mortality. Uter... more ABSTRACTEarly detection of preterm labor is important to avoid neonatal death and mortality. Uterine electromyography (UEMG) or electrohysterography is a non-invasive method of extracting electrica...

Biomedical and Pharmacology Journal, 2018

Early diagnosing is one of the important perinatal challenges for the prevention of preterm birth... more Early diagnosing is one of the important perinatal challenges for the prevention of preterm birth. The electrohysterogram (EHG) or uterine electromyogram (Uterine EMG), collected from the abdominal surface is considered as a biomarker for the prediction or preterm labor. Several features and classifiers have been analyzed in different studies. Four classifiers were applied to two fractal features , say, Higuchi Fractal dimension(HFD) and Detrended Fluctuation Analysis (DFA), after filtering with fourth order band pass filter. The best classification accuracy (95.7989%) was obtained with Elman neural network classifier, when classified DFA feature, with sensitivity 0.9445 and specificity 0.9715.

Biomedical Signal Processing and Control, 2019

Abstract In spite of the tremendous progress of upper limb myoelectric prosthetic control in the ... more Abstract In spite of the tremendous progress of upper limb myoelectric prosthetic control in the field of rehabilitation engineering, there still exist several real world challenges to be met, before realizing it as a good substitute for a natural arm. Incompetence of the system to accommodate variations in contraction levels of muscle movements has been identified as one of the significant challenges, as these variations have a subsequent impact on the performance of pattern recognition based myoelectric control. Non-linear techniques are more suited to characterize myoelectric signals since one of their major properties is nonlinearity. Based on this we propose two feature combinations which can lead to a reliable control scheme that is robust against contraction level variations. The performance of our proposed features when tested on nine transradial amputees for six motion classes at three different force levels outweighed other established feature extraction methods meant for contraction variation independent control. Significant improvement of around 8% in average classification performance was achieved across all subjects and force levels, subjected to training, both with all force levels and with unseen force levels. Moreover, these features achieved superior performance in classifying flexion as well as grip movements.

Future Generation Computer Systems, 2018

Early diagnose for the prevention of preterm birth is one of the important perinatal challenges. ... more Early diagnose for the prevention of preterm birth is one of the important perinatal challenges. The neonatal care and early treatment for preterm babies are increasing the chance of survival, but anyways it affects the respiratory distress, immature brains, cerebral palsy, mental retardation, visual and hearing impairments, and poor health and growth. If preterm labor is diagnosed in the early period of gestation, then it is easy to give an appropriate treatment to the pregnant woman. The uterine electrical activity assessment is a suitable method for monitoring the labor process especially for the prediction of preterm labor. Electrohysterography is a non-invasive technique to monitor the contraction. The electrohysterogram (EHG) or uterine electromyogram (Uterine EMG) is considered as a biomarker for the prediction or preterm labor. A number of studies in this field by various researchers have been reviewed. On the basis of such reviews, this paper provides the different steps such as preprocessing , feature extraction, classifiers and feature subset selection methods for the detection and prediction of preterm birth.

International Journal of Recent Trends in Engineering and Research, 2017

Preterm birth is the major complication during pregnancies. The timely prediction of preterm birt... more Preterm birth is the major complication during pregnancies. The timely prediction of preterm birth can decrease the infant mortality, morbidity as well as the economic costs. This study aimed to predict the premature births using Electrohysterogram (EHG).EHG is a non-invasive diagnostic technique, which measures the electrical activity responsible for the uterine contractions. The abdominal signals were acquired using Ag-AgCl electrodes in a bipolar configuration and the EHG was obtained by bandpass-filtering in the range of .34-1Hz. certain signal features are extracted for classification, linear and binary SVM classifiers are used. The result showed that it is possible to predict the preterm birth with an accuracy of 66.67%, specificity of 83.34% and sensitivity of 50%. Keywords— EHG, Preterm contractions, Bandpass filtering, Linear classifier, Binary SVM classifier.

Procedia Technology, 2016

Cooperative communication in Internet of Things enable the co-existing heterogeneous wireless net... more Cooperative communication in Internet of Things enable the co-existing heterogeneous wireless networks to cooperate with each other in order to facilitate network traffic, guarantee QoS requirements and to enable energy efficient secure communication even to most demanding users. Physical layer security approaches based on node cooperation promise secure communication even in the presence of an eavesdropper. The three main cooperative schemes that help in improving physical layer (PHY) security via cooperative communication are decode-and-forward (DF), amplify-and-forward (AF) and cooperative jamming (CJ). This work mainly focuses on the performance analysis of PHY layer security via two cooperative schemes (DF and AF) by taking all main fading phenomenon's like path loss, phase fading and shadow fading into consideration. Also a method has been discussed for enhancing the secrecy rate by using two heuristic algorithms: "hill-climbing" and "random-search".

Biomedical and Pharmacology Journal, 2019

Proper evaluation and detection of uterine contraction is an important treat during gestation per... more Proper evaluation and detection of uterine contraction is an important treat during gestation period. Uterine contraction happens by the generation of electrical activity from a given myometrial cell to the adjacent cell. There are various methods for monitoring uterine contraction but they lack to distinguish true labour contractions (efficient) from contractions that will not cause delivery (inefficient). One of the most accurate non-invasive technique for monitoring uterine contraction is the uterine electromyogram or Electrohysterogram (EHG). The main aim of this paper is to check whether it is possible to discriminate labour and pregnancy contraction by using 16 electrode database. And also to check bipolar signals give better classification rate than monopolar signals. Result shows that bipolar signal have better performance than monopolar signals.

Intelligent Systems Reference Library, 2019

Prediction of preterm birth is one of the significant perinatal hurdles for the prevention of pre... more Prediction of preterm birth is one of the significant perinatal hurdles for the prevention of preterm birth. The uterine Electromyogram (Uterine EMG), obtained from the abdominal surface is analyzed for the prediction or preterm labor. Many linear and non-linear features and classifiers have been analyzed in different researches. In this paper two neural network classifiers were applied to the Bi-spectrum feature obtained from the Uterine EMG signal. The Bi-spectrum analysis was done after preprocessing the signal. Three pre-processing methods were tried to improve the performance. The best classification accuracy of 99.89% was obtained with Elman neural network classifier when pre-processed with three level wavelet (db4) decomposition. The sensitivity and specificity were found to be 100% and 99.77% respectively.

Wireless Sensor Network (WSN) contains a group of tiny sensor for monitoring and recording of env... more Wireless Sensor Network (WSN) contains a group of tiny sensor for monitoring and recording of environment. And the collected data is transferred to the central location or Base Station (BS). Energy is one of the most important resources of sensor node. Energy utilization can be made efficient by selecting proper routing protocols. This paper discuss about some kind of energy efficient

Ijca Proceedings on National Conference on Vlsi and Embedded Systems, Mar 29, 2013

Linear Prediction Coding (LPC) plays a vital role in speech communication. LPC algorithms are mos... more Linear Prediction Coding (LPC) plays a vital role in speech communication. LPC algorithms are most commonly used for voice coders. In this paper we present a new approach to implement a reconfigurable hardware for sparse LPC algorithms for VoIP applications. The motivation behind this is that the sparser the feature the better would be the bit rate constraint. The necessity of a reconfigurable system is scalability and transcoding. The computational cost is expected to be very low for such a hardware which is capable of solving least square problems.

Biomedical and Pharmacology Journal

This paper evaluates the use of wavelet packet entropy to classify upper limb motions using myoel... more This paper evaluates the use of wavelet packet entropy to classify upper limb motions using myoelectric signals(MES). Being non-stationary, suitable analysis is essential for myoelectric signals recorded at varying force levels. In this paper, different entropy measures calculated from wavelet packet transform coefficients, termed as wavelet packet entropies(WPE) are compared with power spectral entropy and permutation entropy in terms of their performance in myoelectric prosthetic control. The system was trained using MES corresponding to six upper limb movements at three different force levels. WPE feature was found to exhibit better classification accuracy compared to other entropy features. Among the WPE features log-energy WPE outperformed the other four WPE features; while a combination of log-energy and sure WPE yielded the best classification accuracy when used with a simple linear discriminant analysis(LDA) classifier for medium force level testing.