A count data model for heart rate variability forecasting and premature ventricular contraction detection

- Allami, Ragheed, Stranieri, Andrew, Balasubramanian, Venki, Jelinek, Herbert

  • Authors: Allami, Ragheed , Stranieri, Andrew , Balasubramanian, Venki , Jelinek, Herbert
  • Date: 2017
  • Type: Text , Journal article
  • Relation: Signal Image and Video Processing Vol. 11, no. 8 (2017), p. 1427-1435
  • Full Text:
  • Reviewed:
  • Description: Heart rate variability (HRV) measures including the standard deviation of inter-beat variations (SDNN) require at least 5 min of ECG recordings to accurately measure HRV. In this paper, we predict, using counts data derived from a 3-min ECG recording, the 5-min SDNN and also detect premature ventricular contraction (PVC) beats with a high degree of accuracy. The approach uses counts data combined with a Poisson-generated function that requires minimal computational resources and is well suited to remote patient monitoring with wearable sensors that have limited power, storage and processing capacity. The ease of use and accuracy of the algorithm provide opportunity for accurate assessment of HRV and reduce the time taken to review patients in real time. The PVC beat detection is implemented using the same count data model together with knowledge-based rules derived from clinical knowledge.

Multi-variate data fusion technique for reducing sensor errors in intelligent transportation systems

- Manogaran, Gunasekaran, Balasubramanian, Venki, Rawal, Bharat, Saravanan, Vijayalakshmi, Montenegro-Marin, Carlos

  • Authors: Manogaran, Gunasekaran , Balasubramanian, Venki , Rawal, Bharat , Saravanan, Vijayalakshmi , Montenegro-Marin, Carlos
  • Date: 2021
  • Type: Text , Journal article
  • Relation: IEEE Sensors Journal Vol. 21, no. 14 (2021), p. 15564-15573
  • Full Text: false
  • Reviewed:
  • Description: Connected vehicles in intelligent transportation system (ITS) scenario rely on environmental data for supporting user-centric applications along the driving time. Sensors equipped in the vehicles are responsible for accumulating data from the environment, followed by the fusion process. Such fusion process provides accurate and stable data required for the applications in a recurrent manner. In order to enhance the data fusion of connected vehicles, this article introduces multi-variate data fusion (MVDF) technique. This technique is competent in handling asynchronous and discrete data from the environment and streamlining them into continuous and delay-less inputs for the applications. The process of data fusion is aided through least square regression learning to determine the errors in different time instances. The indefinite and definite data fusion instances are differentiated using this regression model to identify the errors in fore-hand. Besides, the differentiation relies on the application run-time interval to progress data fusion within the same or extended time instance and data slots. In this manner the differentiation along with the error identification is regular until the application required data is met. The performance of this technique is verified using network simulator experiments for the metrics error, data utilization ratio, and computation time. The results show that this technique improves data utilization under controlled time and fewer errors. © 2001-2012 IEEE. **Please note that there are multiple authors for this article therefore only the name of the first 5 including Federation University Australia affiliate “Venki Balasubramanian” is provided in this record**.

Smart sensing-enabled decision support system for water scheduling in orange orchard

- Khan, Rahim, Zakarya, Muhammad, Balasubramanian, Venki, Jan, Mian, Menon, Varun

  • Authors: Khan, Rahim , Zakarya, Muhammad , Balasubramanian, Venki , Jan, Mian , Menon, Varun
  • Date: 2021
  • Type: Text , Journal article
  • Relation: IEEE Sensors Journal Vol. 21, no. 16 (2021), p. 17492-17499
  • Full Text:
  • Reviewed:
  • Description: The scarcity of water resources throughout the world demands its optimum utilization in various sectors. Smart Sensing-enabled irrigation management systems are the ideal solutions to ensure the optimum utilization of water resources in the agriculture sector. This paper presents a wireless sensor network-enabled Decision Support System (DSS) for developing a need-based irrigation schedule for the orange orchard. For efficient monitoring of various in-field parameters, our proposed approach uses the latest smart sensing technology such as soil moisture, leaf-wetness, temperature and humidity. The proposed smart sensing-enabled test-bed was deployed in the orange orchard of our institute for approximately one year and successfully adjusted its irrigation schedule according to the needs and demands of the plants. Moreover, a modified Longest Common SubSequence (LCSS) mechanism is integrated with the proposed DSS for distinguishing multi-valued noise from the abrupt changing scenarios. To resolve the concurrent communication problem of two or more wasp-mote sensor boards with a common receiver, an enhanced RTS/CTS handshake mechanism is presented. Our proposed DSS compares the most recently refined data with pre-defined threshold values for efficient water management in the orchard. Irrigation activity is scheduled if water deficit criterion is met and the farmer is informed accordingly. Both the experimental and simulation results show that the proposed scheme performs better in comparison to the existing schemes. © 2001-2012 IEEE.

Marginal and average weight-enabled data aggregation mechanism for the resource-constrained networks

- Jan, Syed, Khan, Rahim, Khan, Fazlullah, Jan, Mian, Balasubramanian, Venki

  • Authors: Jan, Syed , Khan, Rahim , Khan, Fazlullah , Jan, Mian , Balasubramanian, Venki
  • Date: 2021
  • Type: Text , Journal article
  • Relation: Computer Communications Vol. 174, no. (2021), p. 101-108
  • Full Text: false
  • Reviewed:
  • Description: In Wireless Sensor Networks (WSNs), data redundancy is a challenging issue that not only introduces network congestion but also consumes a considerable amount of sensor node resources. Data redundancy occurs due to the spatial and temporal correlation among the data gathered by the neighboring nodes. Data aggregation is a prominent technique that performs in-network filtering of the redundant data and accelerates the knowledge extraction by eliminating the correlated data. However, most of the data aggregation techniques have lower accuracy as they do not cater for erroneous data from faulty nodes and pose an open research challenge. To address this challenge, we have proposed a novel, lightweight, and energy-efficient function-based data aggregation approach for a cluster-based hierarchical WSN. Our proposed approach works at two levels, i.e., at the node level and at the cluster head level. At the node level, the data aggregation is performed using Exponential Moving Average (EMA) and a threshold-based mechanism is adopted to detect any outliers for improving the accuracy of aggregated data. At the cluster head level, we have employed a modified version of Euclidean distance function to provide highly-refined aggregated data to the base station. Our experimental results show that our approach reduces the communication cost, transmission cost, energy consumption at the nodes and cluster heads, and delivers highly-refined and fused data to the base station. © 2021 Elsevier B.V. **Please note that there are multiple authors for this article therefore only the name of the first 5 including Federation University Australia affiliate “Venki Balasubramaniam” is provided in this record**

IoT-powered deep learning brain network for assisting quadriplegic people

- Vinoj, P., Jacob, Sunil, Menon, Varun, Balasubramanian, Venki, Piran, Md Jalil

  • Authors: Vinoj, P. , Jacob, Sunil , Menon, Varun , Balasubramanian, Venki , Piran, Md Jalil
  • Date: 2021
  • Type: Text , Journal article
  • Relation: Computers and Electrical Engineering Vol. 92, no. (2021), p.
  • Full Text: false
  • Reviewed:
  • Description: Brain-Computer Interface (BCI) systems have recently emerged as a prominent technology for assisting paralyzed people. Recovery from paralysis in most patients using the existing BCI-based assistive devices is hindered due to the lack of training and proper supervision. The system's continuous usage results in mental fatigue, owing to a higher user concentration required to execute the mental commands. Moreover, the false-positive rate and lack of constant control of the BCI systems result in user frustration. The proposed framework integrates BCI with a deep learning network in an efficient manner to reduce mental fatigue and frustration. The Deep learning Brain Network (DBN) recognizes the patient's intention for upper limb movement by a deep learning model based on the features extracted during training. DBN correlates and maps the different Electroencephalogram (EEG) patterns of healthy subjects with the identified pattern's upper limb movement. The stroke-affected muscles of the paralyzed are then activated using the obtained superior pattern. The implemented DBN consisting of four healthy subjects and a quadriplegic patient achieved 94% accuracy for various patient movement intentions. The results show that DBN is an excellent tool for providing rehabilitation, and it delivers sustained assistance, even in the absence of caregivers. © 2021
  • 1