SRINIVASAN JAYARAMAN - Academia.edu (original) (raw)

Papers by SRINIVASAN JAYARAMAN

2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE), 2021

Cognitive radio is expected to address several operational challenges like dynamic spectrum acces... more Cognitive radio is expected to address several operational challenges like dynamic spectrum access, spectral heterogeneity and facilitate end-to-end Quality of Service (QOS). The complex nature of cognitive radio is due to its dependency on various network parameters at different levels and ambiguous standards. It is a challenge to address the issues related to effective management of cognitive radio. Issues related to mobility management such as signaling overhead need to be addressed for effectual operation of cognitive radio networks. Signaling enables devices to exchange control information over control channel and helps facilitate data communication. Modern telecommunication-data networks have seen a tremendous increase in signaling and the trend is expected to continue through to the networks of the future. Recent network outrages due to excessive signaling overhead have emphasized the need to develop effective mechanisms to handle signaling overhead. Cognitive radio networks ...

IEEE Journal of Translational Engineering in Health and Medicine, 2017

The last few years has seen a proliferation of wearable electrocardiogram (ECG) devices in the ma... more The last few years has seen a proliferation of wearable electrocardiogram (ECG) devices in the market with applications in fitness tracking, patient monitoring, athletic performance assessment, stress and fatigue detection, and biometrics, to name a few. The majority of these applications rely on the computation of the heart rate (HR) and the so-called heart rate variability (HRV) index via time-, frequency-, or non-linear-domain approaches. Wearable/portable devices, however, are highly susceptible to artifacts, particularly those resultant from movement. These artifacts can hamper HR/HRV measurement, thus pose a serious threat to cardiac monitoring applications. While current solutions rely on ECG enhancement as a pre-processing step prior to HR/HRV calculation, existing artifact removal algorithms still perform poorly under extremely noisy scenarios. To overcome this limitation, we take an alternate approach and propose the use of a spectro-temporal ECG signal representation that we show separates cardiac components from artifacts. More specifically, by quantifying the rate-of-change of ECG spectral components over time, we show that heart rate estimates can be reliably obtained even in extremely noisy signals, thus bypassing the need for ECG enhancement. With such HR measurements in hands, we then propose a new noise-robust HRV index termed MD-HRV (modulation-domain HRV) computed as the standard deviation of the obtained HR values. Experiments with synthetic ECG signals corrupted at various different signal-to-noise levels, as well as recorded noisy signals show the proposed measure outperforming several HRV benchmark parameters computed post wavelet-based enhancement. These findings suggest that the proposed HR measures and derived MD-HRV metric are well-suited for ambulant cardiac monitoring applications, particularly those involving intense movement (e.g., elite athletic training).

Technology Innovation Management Review, 2018

Frontiers in computational neuroscience, 2017

The quantity of music content is rapidly increasing and automated affective tagging of music vide... more The quantity of music content is rapidly increasing and automated affective tagging of music video clips can enable the development of intelligent retrieval, music recommendation, automatic playlist generators, and music browsing interfaces tuned to the users' current desires, preferences, or affective states. To achieve this goal, the field of affective computing has emerged, in particular the development of so-called affective brain-computer interfaces, which measure the user's affective state directly from measured brain waves using non-invasive tools, such as electroencephalography (EEG). Typically, conventional features extracted from the EEG signal have been used, such as frequency subband powers and/or inter-hemispheric power asymmetry indices. More recently, the coupling between EEG and peripheral physiological signals, such as the galvanic skin response (GSR), have also been proposed. Here, we show the importance of EEG amplitude modulations and propose several new ...

Work (Reading, Mass.), Jan 8, 2017

Hand screen-printing (HSP) plays a predominant role in textile industries in developing countries... more Hand screen-printing (HSP) plays a predominant role in textile industries in developing countries. Workers from HSP industry were mostly affected by musculoskeletal injury due to monotonous, and prolonged work nature and poor workplace environment. The present study aims to investigate the prevalence of work-related musculoskeletal disorder (MSD) symptoms and risk factors associated among the HSP industry workers. Cochran's sample size for categorical data was used to select 385 HSP workers of 1000 samples from various provinces of Tamil Nadu, INDIA. Modified Nordic based questionnaire was used to assess the musculoskeletal injuries and risk factors among HSP workers. The statistical analysis revealed that 62.5% workers are prone to MSD symptoms with lower back (75.1%), shoulder (66.2%), knees (58.7%), and ankle/feet (55.6%). Age, experience, marital status, stress in the job were the risk factors which significantly (p < 0.05) associated with the reported MSDs. Further, this...

International Journal of Occupational Medicine and Environmental Health, 2017

This study aims to assess muscle fatigue for kitchen workers during various tasks in a kitchen. M... more This study aims to assess muscle fatigue for kitchen workers during various tasks in a kitchen. Material and Methods: This study consists of 2 phases: a) surface electromyography (EMG) to determine muscle fatigue of trapezius and erector spinae muscles bilaterally for 12 healthy male volunteers during 30 min of Indian flatbread (chapati) preparation, b) self-administered questionnaire study after 30 min preparation to determine the impact on performance. Results: Surface EMG results show that the right trapezius muscle had significantly higher fatigue during kneading, rolling and roasting tasks. Similarly, right erector spinae muscle showed significantly higher fatigue during rolling and roasting tasks. Conclusions: Both phases of the study conclude that, even though the dynamic postural adjustment may reduce fatigue during the work schedule; the combination of risk factors like the repetitive task, forceful exertion and prolonged standing during working results in a high risk of developing muscle fatigue.

This study aims to assess commercial advertisement (Ads) using EEG signal at frontal lobes. In ad... more This study aims to assess commercial advertisement (Ads) using EEG signal at frontal lobes. In addendum, the behaviors of left and right hemisphere frontal cortical activities were evaluated to determine the effects of emotion during Ads. EEG signals were recorded for fifteen healthy volunteers at frontal (F3, F4, F7, F8, AF3 and AF4) lobes on the cranium for six advertisements (Animation, Narrative, Culture, Celebrities, Music, Speech marketing). Raw EEG signals were processed, artifacts were removed and relative wavelet packet energy calculation was performed. Result indicates that theta activity was significantly (p<0.05) higher in left lobe during animation and speech advertisement and lower for narrative, culture and music ads compared to right lobe. Decrease in theta activity in left and right frontal lobe reflects positive and negative emotion respectively. Study infers, narrative, celebrities and music advertisement have positive emotion (like) for viewers and animation a...

In the past decade, remarkable progress has been made towards the multimedia data retrieval; howe... more In the past decade, remarkable progress has been made towards the multimedia data retrieval; however there is a challenging need for efficient and realistic image retrieval model. One such approach for image retrieval is content based technique. In this pilot study, we have proposed a new algorithm for digital image indexing and retrieval using wavelet based block processing approach. Original image has been converted into HSV co-ordinate and it has been divided into 4x4 pixel block. A block clustering algorithm is applied for image segmentation using K-means algorithm. Feature parameters were extracted from each cluster and have been stored for future use. At the time of image query, the feature vectors of the query image were collected and Euclidean distance between each region is computed. The result has been sorted in descending order based on vector value. Results demonstrate that, our image retrieval system improves the accuracy and robustness. In future, same technique could be used for automatic diagnosing of medical images and also for health care sector; for patient database maintenance.

Journal of back and musculoskeletal rehabilitation, Jan 15, 2014

The occurrence of specific low back pain (LBP) due to workplace factors has not been well describ... more The occurrence of specific low back pain (LBP) due to workplace factors has not been well described among kitchen industry workers. This study would claim various risk factors that contributing LBP among kitchen workers. The purpose of the study was to examine the risk factors and the prevalence of LBP among the male commercial kitchen workers at catering industry. The study population comprised of 114 male kitchen workers from nine hostel kitchens in a college campus in South India. The reported musculoskeletal symptoms during past 12 months were determined with the help of standardized Nordic Musculoskeletal Questionnaire (NMQ) survey and by direct observations. The statistical analyses were carried out and the highest prevalence of LBP among subjects was reported as 65.8%. Among different work categories, the Chief cooks were reported highest prevalence of LBP (79.2%) than Assistant Cooks (71.4%) and Kitchen Aids (30.0%). Similarly the upper age group (⩾ 41 years) workers had exp...

Biomedical Engineering / 765: Telehealth / 766: Assistive Technologies, 2012

ABSTRACT Aim of the study is to develop a wearable device that continuously monitors the cardiac ... more ABSTRACT Aim of the study is to develop a wearable device that continuously monitors the cardiac and mobility of an individual; especially for the elderly and critical care patients. In addition to this, an inbuilt decision support (DS) algorithm, to analyze the ECG signal in correlation with mobility activity and generate an alert message. This event based alert message is sent to the physician or user through Bluetooth protocol on encountering any arrhythmia. Developed wearable device provides connectivity to two participants: the user or nurse at the point of home care, and the physician. At the out of hospital point of care, during users fall condition scenario, ECG signals are recorded in the SD card. This action is followed by alert generation which gives the heart rate and filename information in which the ECG data has been stored for easy review of the physician. Based on request, ECG data is transmitted to user mobile phone via Bluetooth and stored in server, linked to the patient's database. The cardiologist can then be linked by means of a web browser to the information server to diagnosis the ECG signal based on the event. In future, this study can be extended to improve the arrhythmia detection algorithm by analysis of mobility data like jogging, running and etc along with ECG data monitoring. The developed system can then be used as a continuous wireless cardiac device with mobility monitoring for clinical diagnosis support.

2011 Defense Science Research Conference and Expo (DSR), 2011

Abstract ECG is a valuable source of information regarding the patient's clinical data repos... more Abstract ECG is a valuable source of information regarding the patient's clinical data repository. Archiving the paper Electrocardiogram (ECG) trace as an image requires immense storage space and manpower for storage and retrieval of the patient records. ...

Lecture Notes in Computer Science, 2011

Today’s high-end computer systems contain technologies that only few individuals could have imagi... more Today’s high-end computer systems contain technologies that only few individuals could have imagined a few years ago. However the conscious input device ergonomics design is still lagging; for example, the extensive usage of computer mouse results in various upper extremity musculoskeletal disorders. This endower towards the developed of HSI system, that act as an alternative or replacement device for computer mouse; thereby one could avoid musculoskeletal disorders. On the other hand, the developed system can also act as an aid tool for individuals with upper extremity disabled. The above issue can be addressed by developing a framework for Human System Interface (HSI) using biological signal as an input signal. The objective of this paper is to develop the framework for HSI system using Surface Electromyogram for individuals with various degrees of upper extremity disabilities. This framework involves the data acquisition of muscle activity, translator algorithm that analysis and translate the EMG as control signal and a platform independent tool to provide mouse cursor control. Thus developed HSI system is validate on applications like web-browsing, simple arithmetic calculation with the help of GUI tool designed.

2010 20th International Conference on Pattern Recognition, 2010

This paper proposes a new approach for person identification and novel person authentication usin... more This paper proposes a new approach for person identification and novel person authentication using single lead human Electrocardiogram. Nine Feature parameters were extracted from ECG in spatial domain for classification. For person identification, Dynamic Time Warping (DTW) and Fisher's Linear Discriminant Analysis (FLDA) with K-Nearest Neighbor Classifier (NNC) as single stage classification yielded a recognition accuracy of 96% and 97% respectively. To further improve the performance of the system, two stage classification techniques have been adapted. In two stage classifications FLDA is used with k-NNC at the first stage followed by DTW classifier at the second stage which yielded 100% recognition accuracy. During person authentication we adapted the QRS complex based threshold technique. The overall performance of the system was 96% for both legal and intruder situations is verified for MIT-BIH normal database size of 375 recording from 15 individual ECG.

ipcbee.com

Abstract. Electrocardiogram (ECG) has been the preliminary diagnostic tool to detect cardiovascul... more Abstract. Electrocardiogram (ECG) has been the preliminary diagnostic tool to detect cardiovascular diseases. ECG is generally recorded on a thermal paper which cannot be stored for a long time for analysis, as the thermal trace gets erased gradually. To store the ...

IEEE International Conference on Electronics Design …, 2009

ABSTRACT Changes in the normal heart rhythm would lead to various kinds of cardiac arrhythmias or... more ABSTRACT Changes in the normal heart rhythm would lead to various kinds of cardiac arrhythmias or rhythm disorders. If such rhythm disorders are sustained over long periods of time, then it would cause immediately fatal or irreparable damage to the heart. Cardiac issues in developing countries like India have serious issues and they had their effect in road accidents as well. In addition to direct collusion of vehicle due to heart attack, they leave their impact indirectly on other vehicle as well. The present work aims to reduce the indirect impact of road accidents by providing a safe breaking system based on biological cardiac signals. In this paper, we describe a novel concept for electrocardiogram (ECG) system intended for continuous monitoring of the heart rhythms; especially de-signed and developed for detection of cardiac-arrhythmias of drivers during driving. Individuals will wear the ECG sensor while driving. ECG device continuously acquires and monitors the ECG signals and detects the abnormalities using developed automatic arrhythmia detection algorithm. Based on this, a control signal will be sent to motor driver and vehicle will be halted or stopped. In addition, this device will act as a contin-uous recorder; that can be used for clinical diagnosis for a person surviving with cardiac arrest.

Journal of Bodywork and Movement Therapies, 2009

In this study, we determined the muscle activity of aerobic cyclist on biceps brachii medial, tra... more In this study, we determined the muscle activity of aerobic cyclist on biceps brachii medial, trapezius medial, latissimus dorsi medial, and erector spinae muscles bilaterally during 30 min of cycling. Thirteen male volunteers were chosen and placed in two groups (with and without low back pain (LBP)). Surface electromyography (sEMG) was recorded bilaterally from selected muscle groups for 30 min of cycling for each subject. Statistical tests were performed to determine the difference in fatigue, using mean power frequency difference. LBP group showed a significantly higher fatigue (po0.05) in left biceps brachii medial when compared to the control group. High fatigue in the back muscles in the LBP group was not found; however, when linear regression was performed for these individuals, the data showed a possibility of worsening in their condition due to 30 min of cycling.