Revisiting signal processing with spectrogram analysis on EEG, ECG and speech signals

Wang, Weijie; Zhang, Gaopeng; Yang, Luming; Balaji, V. S.; Elamaran, V.; Arunkumar, N.

doi:10.1016/j.future.2018.12.060

Cited by 44 publications

(12 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It is commonly used for prototyping and functional verification of ASICs (application-specific integrated circuits). FPGAs are significantly faster in applications where simultaneous computing is required for various processes due to their unique parallel computing capability [ 13 , 33 ].…”

Section: Methodsmentioning

confidence: 99%

“…Different methods such as digital signal processing and image processing, wavelet transform, empirical mode decomposition, neural networks, and Markov models would help clinicians to secure a better clinical diagnosis. Rapid advancements in computational biology, biomechanics, biomedical, biological, diagnostic imaging, and numerical techniques have created a unique opportunity to leverage traditional computer models for a variety of biological systems to build modern diagnostic tools [ 13 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Reconfigurable Architectures with High-Frequency Noise Suppression for Wearable ECG Devices

Jerard

Thilagaraj

Pandiaraj

et al. 2021

Journal of Healthcare Engineering

Self Cite

View full text Add to dashboard Cite

Recent advances in electronics and microelectronics have aided the development of low-cost devices that are widely used as well-being or preventive monitoring devices by many people. Remote health monitoring, which includes wearable sensors, actuators, and modern communication and information systems, offers effective programs that allow people to live peacefully in their own homes while also being protected in some way. High-frequency noise, power-line interface, and baseline drift are prevalent during the data-acquisition system of an ECG signal, and they can limit signal understanding. They (noises) must be isolated in order to provide an appropriate diagnostic of the patient. When removing high-frequency components (noise) from an ECG signal with an FIR filter, the critical path delay increases considerably as the filter's duration increases. To reduce high-frequency noise, simple moving average filters with pipelining and look-ahead transformation techniques are extensively used in this study. With the use of pipelining and look-ahead techniques, the only objective is to increase the clock speed of the designs. The moving average filters (conventional and proposed) were created on an Altera Cyclone IV FPGA EP4CE115F29C7 chip using the Quartus II software v13.1 tool. Finally, performance metrics such logic elements, clock speed, and power consumption were compared and studied thoroughly. The recursive pipelined 8-tap MA filter with look-ahead approach outperforms the other designs (685.48 MHz) in this investigation.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Reconfigurable Architectures with High-Frequency Noise Suppression for Wearable ECG Devices

Jerard

Thilagaraj

Pandiaraj

et al. 2021

Journal of Healthcare Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…A spectrogram reconstructs 2D images while maintaining the information contained in 1D time series data [14]. Spectrograms are useful for visually describing changes in the frequency characteristics of nonstationary signals, such as physiological signals over time [15,16]. Spectrograms can be generated by repeating short-time Fourier transforms that divide a longer time signal into shorter segments of equal length and then computing the Fourier transforms separately on each shorter segment.…”

Section: Spectrogrammentioning

confidence: 99%

Novel Analgesic Index for Postoperative Pain Assessment Based on a Photoplethysmographic Spectrogram and Convolutional Neural Network: Observational Study

2021

View full text Add to dashboard Cite

Background Although commercially available analgesic indices based on biosignal processing have been used to quantify nociception during general anesthesia, their performance is low in conscious patients. Therefore, there is a need to develop a new analgesic index with improved performance to quantify postoperative pain in conscious patients. Objective This study aimed to develop a new analgesic index using photoplethysmogram (PPG) spectrograms and a convolutional neural network (CNN) to objectively assess pain in conscious patients. Methods PPGs were obtained from a group of surgical patients for 6 minutes both in the absence (preoperatively) and in the presence (postoperatively) of pain. Then, the PPG data of the latter 5 minutes were used for analysis. Based on the PPGs and a CNN, we developed a spectrogram–CNN index for pain assessment. The area under the curve (AUC) of the receiver-operating characteristic curve was measured to evaluate the performance of the 2 indices. Results PPGs from 100 patients were used to develop the spectrogram–CNN index. When there was pain, the mean (95% CI) spectrogram–CNN index value increased significantly—baseline: 28.5 (24.2-30.7) versus recovery area: 65.7 (60.5-68.3); P<.01. The AUC and balanced accuracy were 0.76 and 71.4%, respectively. The spectrogram–CNN index cutoff value for detecting pain was 48, with a sensitivity of 68.3% and specificity of 73.8%. Conclusions Although there were limitations to the study design, we confirmed that the spectrogram–CNN index can efficiently detect postoperative pain in conscious patients. Further studies are required to assess the spectrogram–CNN index’s feasibility and prevent overfitting to various populations, including patients under general anesthesia. Trial Registration Clinical Research Information Service KCT0002080; https://cris.nih.go.kr/cris/search/search_result_st01.jsp?seq=6638

show abstract

“…Furthermore, the type of signal will determine the processing that can be applied. The processing methods chosen in this work are in both, time and frequency domain, selecting those that, according to the literature, are commonly used in the analysis of mentioned signals [27].…”

Section: Theory Topics Covered In the Coursementioning

confidence: 99%

Constructivism-Based Methodology for Teaching Artificial Intelligence Topics Focused on Sustainable Development

2019

View full text Add to dashboard Cite

This article proposes the creation of a course based on a series of practical sessions, where the students have to develop their practical knowledge about artificial intelligence techniques, specifically multilayer perceptron. The novelty of this paper is based on the constructivism methodology regarding artificial intelligence and sustainable development. Moreover, it can be implemented in different majors because of the flexibility in certain aspects. It is oriented to evaluate skills in the broad education necessary to understand the impact of engineering solutions in a global, economic, environmental, and societal context. The proposal helps the students to turn theoretical concepts into more tangible objects where they can build their knowledge by programming their implementations in software. Then, programming codes for practicing the neural networks theory, finite impulse response, empirical mode decomposition and discrete wavelet transform are achieved to compare percentage classification between different techniques. Also, it measures the interaction between the student and the theoretical mathematics of artificial intelligence. The continuous evaluations at the end of the practical sessions corroborate the increase in the knowledge of the students. A study based on rubrics illustrates an increase in the average grade obtained by the students in the elaboration of each practice. Finally, a senior project is carried out by taking into account sustainable development issues and the usage of tools of artificial intelligence.

show abstract

Revisiting signal processing with spectrogram analysis on EEG, ECG and speech signals

Cited by 44 publications

References 3 publications

Reconfigurable Architectures with High-Frequency Noise Suppression for Wearable ECG Devices

Reconfigurable Architectures with High-Frequency Noise Suppression for Wearable ECG Devices

Novel Analgesic Index for Postoperative Pain Assessment Based on a Photoplethysmographic Spectrogram and Convolutional Neural Network: Observational Study

Constructivism-Based Methodology for Teaching Artificial Intelligence Topics Focused on Sustainable Development

Contact Info

Product

Resources

About