Search

• In this article, the CPSC 2018 dataset was used to train a ResRNN model. To classify the diseases into nine categories: normal, Arrhythmia (AF), I-atrioventricular block (AVB), left bundle branch block (LBBB), right bundle branch block (RBBB), premature atrial contraction (PAC), premature ventricular contractions (PVC), ST-segment depression (STD), ST-segment elevation (STSE) /(STE). • The ResRNN outperforms in identifying eight types of anomalies in 12-lead ECG data. • When level 4 rough coefficients with the Symlet-8 (Sym8) channel were used for organization, the best degree of exactness was obtained. • The ResRNN classifier has a normal accuracy of 91 percent when using ECG signals, which is much higher than the deep multiscale fusion neural network (DesNet) at 83 % and inception ResNet V2 at 80 %. Automated electrocardiogram (ECG) analysis cannot be employed in clinical practice due to the accuracy of the present models. Deep Neural Networks (DNNs) are models made up of stacking transformations that learn tasks by example. This technology has lately demonstrated remarkable performance in several activities, and its potential to improve clinical practice is highly anticipated. In this article, the China physiological signal challenge (CPSC)- 2018 dataset was used to train a ResRNN model. The ResRNN outperforms in identifying eight types of anomalies in 12-lead ECG data. When level 4 rough coefficients with the Symlet-8 (Sym8) channel were used for organization, the best degree of exactness was obtained. The ResRNN classifier has a normal accuracy of 91% when using ECG signals, which is much higher than the deep multiscale fusion neural network (DesNet) at 83 % and Inception ResNet V 2 at 80 %. As a result, the given methodology is far better than others. After preprocessing the signals, the ResRNN model classifies the diseases into nine categories: normal, Atrial fibrillation (AF), first degree-atrioventricular block (AVB), left bundle branch block (LBBB), right bundle branch block (RBBB), premature atrial contraction (PAC), premature ventricular contractions (PVC), ST-segment depression (STD), and ST-segment elevation (STSE) /(STE). [ABSTRACT FROM AUTHOR]

• In this article, the CPSC 2018 dataset was used to train a ResRNN model. To classify the diseases into nine categories: normal, Arrhythmia (AF), I-atrioventricular block (AVB), left bundle branch block (LBBB), right bundle branch block (RBBB), premature atrial contraction (PAC), premature ventricular contractions (PVC), ST-segment depression (STD), ST-segment elevation (STSE) /(STE). • The ResRNN outperforms in identifying eight types of anomalies in 12-lead ECG data. • When level 4 rough coefficients with the Symlet-8 (Sym8) channel were used for organization, the best degree of exactness was obtained. • The ResRNN classifier has a normal accuracy of 91 percent when using ECG signals, which is much higher than the deep multiscale fusion neural network (DesNet) at 83 % and inception ResNet V2 at 80 %. Automated electrocardiogram (ECG) analysis cannot be employed in clinical practice due to the accuracy of the present models. Deep Neural Networks (DNNs) are models made up of stacking transformations that learn tasks by example. This technology has lately demonstrated remarkable performance in several activities, and its potential to improve clinical practice is highly anticipated. In this article, the China physiological signal challenge (CPSC)- 2018 dataset was used to train a ResRNN model. The ResRNN outperforms in identifying eight types of anomalies in 12-lead ECG data. When level 4 rough coefficients with the Symlet-8 (Sym8) channel were used for organization, the best degree of exactness was obtained. The ResRNN classifier has a normal accuracy of 91% when using ECG signals, which is much higher than the deep multiscale fusion neural network (DesNet) at 83 % and Inception ResNet V 2 at 80 %. As a result, the given methodology is far better than others. After preprocessing the signals, the ResRNN model classifies the diseases into nine categories: normal, Atrial fibrillation (AF), first degree-atrioventricular block (AVB), left bundle branch block (LBBB), right bundle branch block (RBBB), premature atrial contraction (PAC), premature ventricular contractions (PVC), ST-segment depression (STD), and ST-segment elevation (STSE) /(STE). [ABSTRACT FROM AUTHOR]

A lot of algorithms are available to optimize the heating level to maintain room temperature. In this paper a low cost and energy efficient control system is proposed which comprises of three sections- sensor node, heater node and remote control. For testing, 2kw heater is placed in 20*10*10 cubic feet room area and is controlled through remote control based on Zigbee protocol. Remote control is used to set the desired temperature of heating system. The two temperature nodes are placed in appropriate diagonal location in the room and send the value of room temperature to the heater node. Heater node takes the average of the two sensor nodes and provides feedback to heater system. This is an intelligent network in which heater node intelligently maintains the room temperature by generating error signal with set value from remote and received average value from sensor nodes. Then value of K P , K I , K D is calculated by using PID and hybrid Particle Swarm Optimizing (HPSO) algorithm and adjust the voltage levels of heating element. Heater node is capable to communicate with sensor nodes upto 30 meters and with remote control upto 100 meters. It is observed that upto 16.94% energy can be saved by using proposed system. [ABSTRACT FROM AUTHOR]

In this era of modernization, lots of systems have been introduced by which the human effort has been limited to a certain level. In this Paper a data acquisition system has been proposed for factories and industries or environment monitoring, which will measure the certain parameters like temperature, humidity, the level of gases present in atmosphere, motion of any person near the restricted areas at a time and transmit these parameters to the control room wirelessly as well as to the concerned person of the area by the latest smartphone/tablets. Through the smartphone, the person can give command to the control room in case of any parameter crosses a certain level. The data is collected from sensor nodes to the control room node using ZigBee network and then retransmit the desired data to smart phones, tabs and PCs using Bluetooth network. Sensor node contains analog output sensors like temperature, gas and Digital output sensors like sound and metal. The LCD is used to display the sensor parameters. The RF modem is used to transmit the values to the control room node using star and mesh network topologies. The control room node contains ZigBee transceiver module to receive the information and Bluetooth modem to make available the desired data to the smart phones, tabs and PCs. The ZigBee and Bluetooth network are working at 9600 baud rate and 2.4 GHz frequency in ISM band. The ZigBee nodes are capable to transmit the information upto 100meteres and for long distance communication, multi-hopping is used. Bluetooth modem is capable to transmit the information upto 30 feet distance. [ABSTRACT FROM AUTHOR]

A drastic change in environmental conditions and geographical conditions causes big disasters. To save lives, monitoring of these changes is a big challenge. Along with monitoring, corresponding action to be taken within time limit is also important. To achieve this objective timely information about it is required. In this paper a Zigbee based system is proposed for disaster monitoring and management. Paper talks about wireless monitoring of water levels of group of dams and due to drastic change in water level in any river/lake, when to open the gate of which dam and upto which limit. It is decided with the help of sensory data collected from different nodes, placed over an area. The system comprises three parts, sensor nodes, local control room and centre control room. The monitoring is done with the help of data collected from sensor nodes(comprising water level sensor and rain sensor) and discharge sensors are used to control the opening of gates upto certain limit. All the decisions are taken through centre control room, by giving commands to different local control rooms after observing conditions of all areas. A hooter is also available with local control room node to indicate danger alert if water level crosses danger level. [ABSTRACT FROM AUTHOR]