Abstract:
Identification of pulmonary diseases involves accurate auscultation as well as elaborate and expensive pulmonary function tests. Also, there is a dependency on a reference signal from a flowmeter or need for labelled respiratory phases. The present disclosure provides extraction of frequency and time-frequency domain lung sound features such as spectral and spectrogram features respectively that enable classification of healthy and abnormal lung sounds without the dependencies of prior art. Furthermore extraction of wavelet and cepstral features improves accuracy of classification. The lung sound signals are pre-processed prior to feature extraction to eliminate heart sounds and reduce computational requirements while ensuring that information providing adequate discrimination between healthy and abnormal lung sounds is not lost.
Abstract:
This disclosure relates generally to telecommunication networks, and more particularly to a method and system for delay aware uplink scheduling in a communication network. The telecommunication network performs data uplink and data downlink associated with data communication between multiple transmitter-receiver pairs connected to the network, by using specific scheduling schema as part of the data processing. Disclosed are method and system for performing a delay-aware uplink scheduling in the communication network. For an uplink request received from a transmitter, the system estimates downlink delay at the corresponding receiver side. The system further estimates a processing delay for the received uplink request. Based on the estimated downlink delay and the processing delay, the system determines an uplink delay budget for the transmitter. Further, based on the uplink delay budget and an achievable data rate computed for the transmitter, the system schedules uplink for the transmitter.
Abstract:
The present disclosure provides a non-invasive, inexpensive and unobtrusive system that enables heart rate (HR) monitoring by addressing the traditionally known issues with face video based systems due to respiration, facial expressions, out-of-plane movements, camera parameters and environmental factors. These issues are alleviated by filtering, pulse modelling and HR tracking. Quality measures are defined which incorporate out-of-plane movements to define the quality of each video frame unlike existing approaches which provide a single quality for the entire video. To handle out-of-plane movement, Fourier basis function is employed to reconstruct pulse signals at affected locations. Bayesian decision theory based method performs HR tracking using previous HR and quality estimates for improved HR monitoring.
Abstract:
A system and method for real time estimation of heart rate (HR) from one or more face videos acquired in non-invasive manner. The system receives face videos and obtains several blocks as ROI consisting of facial skin areas. Subsequently, the temporal fragments are extracted from the blocks and filtered to minimize the noise. In the next stage, several temporal fragments are extracted from the video. The several temporal fragments, corrupted by noise are determined using an image processing range filter and pruned for further processing. The HR of each temporal fragment, referred as local HR is estimated along with its quality. Eventually, a quality based fusion is applied to estimate a global HR corresponding to the received face videos. In addition, the disclosure herein is also applicable for frontal, profile and multiple faces and performs in real-time.
Abstract:
A pulmonary health monitoring system aims at assessing pulmonary health of subjects. Conventional techniques used for pulmonary health monitoring are not convenient to the subjects and needs considerable cooperation from the subjects. But, there is a challenge in utilizing the conventional devices to the subjects not capable of providing considerable cooperation. The present disclosure includes a blow device applicable to all kind of subjects and doesn't need cooperation from the subjects. Further, in the present disclosure, the blow device generates a phase shifted signal corresponding to a breathe signal and the phase shifted signal is further processed to extract a set of physiological features. Further, pulmonary health of a subject is analyzed by processing the set of physiological features based on a ridge regression based machine learning technique.
Abstract:
A physiological parameter measurement device comprising a processor and a video processing module coupled to the processor to divide each of a plurality of frames of a video into a plurality of blocks, where the video is of a body part of a subject whose physiological parameter is to be determined. The video processing module further is to select a block having highest peak signal to noise ratio (PSNR) from amongst the plurality of blocks. Further, the video processing module is to extract a photoplethysmogram (PPG) signal from the video based on a block identifier associated with the block. The physiological parameter measurement device further comprises a signal enhancement module coupled to the processor, to process the PPG signal to obtain an enhanced PPG signal for determining a value of the physiological parameter for the subject.
Abstract:
A method and system of detecting arrhythmia using photoplethysmogram (PPG) signal is provided. The method is performed by extracting photoplethysmogram (PPG) signals from a patient, extracting cardiac parameter from the extracted photoplethysmogram (PPG) signals, identifying presence of cardiac abnormalities as reinforcement filtering of detecting premature ventricular contraction and ventricular flutter from the extracted cardiac parameters, analysing the extracted cardiac parameters to investigate statistical trend and to perform statistical closeness approximation of the extracted photoplethysmogram (PPG) signals and predicting and subsequently classifying type of arrhythmia.
Abstract:
The present invention discloses a method and a system for enhancing accuracy of human counting in at least one frame of a captured image in a real-time in a predefined area. The present invention detects human in one or more frames by using at least one human detection modality for obtaining the characteristic result of the captured image. The invention further calculates an activity probability associated with each human detection modality. The characteristic results and the activity probability are selectively integrated by using a fusion technique for enhancing the accuracy of the human count and for selecting the most accurate human detection modality. The human is then performed based on the selection of the most accurate human detection modality.
Abstract:
A system and method for resource utilization in a constrained sensor gateway for transfer of data in terms of the bandwidth and energy available to transfer data. The system includes a processor in communication with the constrained sensor gateway, which includes an application layer protocol and which is in communication with a communication network, and a memory coupled to the processor. The memory includes a network condition detection module configured to detect a network condition of the constrained sensor gateway, and an adaption module configured to determine a reliability score. The application layer protocol of the constrained sensor gateway adapts a reliability level based on the reliability score determined by the adaption module, which enables better utilization of the bandwidth and energy to transfer data. The reliability level may pertain to a reliable mode, or a non-reliable mode of communication for transferring data.
Abstract:
A method, system and apparatus for determining crowdedness at a location, using a first portable communication device having a proximity sensor, wherein the location of a first user is determined using the first portable communication device having an application installed on a memory module thereof, wherein the application is configured to connect to a location sensor embedded in the first portable communication device. The method and system further comprises sensing and identifying a second portable communication device in vicinity of the first user, followed by transmitting a media access control address (MAC address) of the identified second portable communication device to a remote fusion server. Further removing redundancies pertaining to the identified second portable communication device based on the MAC address received by the remote fusion server using a fusion algorithm to determine the crowdedness at the determined location.