Academic Profile : Faculty

Assoc Prof Ser Wee.JPG picture
Assoc Prof Ser Wee
Emeritus Associate Professor, School of Electrical & Electronic Engineering
 
Prof. Ser has been with the School of EEE since 1997. Prior to joining NTU, he was a Research Devision Head and Technological Advisor to the CEO of DSO National Laboratories. He received his Bachelor and Ph.D. degrees from the Loughborough University, UK. His research interests include sensor array signal processing and signal classification techniques. He has published more than 100 papers in international journals and conferences. He is the receipient of the Columba Plan Scholarship, the PSC Postgraduate Scholarship, an IEE Prize, a Defence Technology Prize, a DSO Excellence Award, and a best paper on speech processing presented at an international conference. He is an inventor/co-inventor of 6 patents and one pending patent. He is a senior member of the IEEE.

Prof. Ser is an associate editor for the IEEE Communications Letters and the Journal of Multidimensional Systems and Signal Processing. He has been a reviewer for several prestiguous international journals (IEEE Transaction on Signal Processing, IEEE Transaction on Audio, Speech and Language Processing, IEEE Transactions on Circuit and Systems, IEEE Signal Processing Letters, IEEE Journal of Selected Area of Communications, IEEE Communications Letters) and conferences (ICC, VTC, ISCAS, SIPS, etc.). He is a TC member of the IEEE Circuit and Systems Society and he has served as Chairman for the IEEE Signal Processing Chapter (Singapore).

Prof. Ser has also served in international and national advisory and technical committees and as panel chair and speakers for several international symposium/workshop. He is currently a member of the IDM Expert Group set up by the National Research Foundation.
Prof Ser's expertise areas are sensor array signal processing and signal classification techniques.

His current research works focus on robust beamforming and DOA estimation techniques for microphone array, location estimatin techinques for ambient intelligence, detection and classification techniques for sound based as well as radiowave based healthcare and surveillance applciations, integrated audio-video signal processing, audio scene analysis and speech emotion analysis for natural human-computer interaction, as well as EEG brain signal analysis.
 
US-2019-0125263-A1 : System And Method For Health Condition Monitoring (2021)
Abstract: A system for health condition monitoring includes a wearable device, a portable device and a server. The portable device is capable of communicating between the wearable device and the server. The system further includes a non-contact ECG acquisition module for capturing ECG signals from a user wearing the wearable device, a non-contact audio acquisition module for capturing a respiratory sound signal and a heart sound signal from the user wearing the wearable device, a first signal processing and analysis module for receiving and processing the ECG signals, the respiratory sound signal and the heart sound signal to perform QRS detection, HR calculation and ECG derived RR determination, and a second signal processing and analysis module for receiving and processing the ECG signals, the respiratory sound signal and the heart sound signal to perform heart sound localization, heart sound cancellation, respiratory sound restoration, and sound based RR determination.

US 2019/0038216 A1: Methods For Detecting A Sleep Disorder And Sleep Disorder Detection Devices (2021)
Abstract: According to various embodiments, there is provided a method for detecting a sleep disorder, the method including: processing an audio signal, the audio signal including breathing sounds made by a subject when the subject is asleep; identifying intervals of the audio signal where breathing sounds are absent; and detecting the sleep disorder based on the identified intervals.

US 2015/0190091 A1: Device, System And Method For Detection Of Fluid Accumulation (2019)
Abstract: A method of detecting a level of fluid accumulation in an internal organ of a subject is proposed, as well as a system for carrying out the method. The method comprises: providing at least one classifier trained to distinguish between two or more levels of fluid accumulation; acquiring an audio signal (110) generated by said internal organ; and processing, using at least one processor (134), said audio signal (110) by: performing feature extraction to generate at least one feature vector from the audio signal; and assigning a fluid level from the two or more levels to the audio signal by passing the at least one feature vector to the at least one classifier.

US 2013/0102908 A1: An Air Conduction Sensor and a System and a Method for Monitoring a Health Condition (2017)
Abstract: According to embodiments of the present invention, an air conduction sensor for detecting a sound from a user is provided. The air conduction sensor includes a housing comprising an opening, wherein a rim of the opening is configured to at least substantially attach to a skin or a clothing of the user; a microphone coupled to the housing such that there is an air gap between the microphone and the skin or the clothing, and wherein the microphone is configured to detect the sound. A system and a method for monitoring a health condition of a user are also provided.

US 2014/0257063 A1: Method Of Predicting Acute Cardiopulmonary Events And Survivability Of A Patient (2015)
Abstract: A method of producing an artificial neural network capable of predicting the survivability of a patient, including: storing in an electronic database patient health data comprising a plurality of sets of data, each set having at least one of a first parameter relating to heart rate variability data and a second parameter relating to vital sign data, each set further having a third parameter relating to patient survivability; providing a network of nodes interconnected to form an artificial neural network, the nodes comprising a plurality of artificial neurons, each artificial neuron having at least one input with an associated weight; and training the artificial neural network using the patient health data such that the associated weight of the at least one input of each artificial neuron is adjusted in response to respective first, second and third parameters of different sets of data from the patient health data.

US 2014/0187988 A1: Method Of Predicting Acute Cardiopulmonary Events And Survivability Of A Patient (2015)
Abstract: A method of producing an artificial neural network capable of predicting the survivability of a patient, including: storing in an electronic database patient health data comprising a plurality of sets of data, each set having at least one of a first parameter relating to heart rate variability data and a second parameter relating to vital sign data, each set further having a third parameter relating to patient survivability; providing a network of nodes interconnected to form an artificial neural network, the nodes comprising a plurality of artificial neurons, each artificial neuron having at least one input with an associated weight; and training the artificial neural network using the patient health data such that the associated weight of the at least one input of each artificial neuron is adjusted in response to respective first, second and third parameters of different sets of data from the patient health data.