Many various Multi-sensor Data Fusion Algorithms for different objectives (from activity recognition to emotion detection) were defined and then implemented using the different SPINE frameworks.

Main review papers:

  • Raffaele Gravina, Parastoo Alinia, Hassan Ghasemzadeh, Giancarlo Fortino, “Multi-sensor fusion in body sensor networks: State-of-the-art and research challenges,” Information Fusion, Volume 35, 2017, Pages 68-80, ISSN 1566-2535, https://doi.org/10.1016/j.inffus.2016.09.005. [Highly Cited Paper/Web of Science]
  • Qimeng Li, Raffaele Gravina, Ye Li, Saeed H. Alsamhi, Fangmin Sun, Giancarlo Fortino: Multi-user activity recognition: Challenges and opportunities. Inf. Fusion 63: 121-135 (2020)

List of the algorithms

  • Activity Recognition based on body-worn inertial sensors and traditional machine learning – Implementation based on SPINE1
    • G. Fortino, R. Gravina, W. Russo, Activity-aaService: Cloud-assisted, BSN-based system for physical activity monitoring, 19th IEEE International Conference on Computer Supported Cooperative Work in Design (CSCWD 2015), Falerna, Italy, May 2015.
    • R. Giannantonio, R. Gravina, P. Kuryloski, V. Seppa, F. Bellifemine, J. Hyttinen, and M. Sgroi. Performance analysis of an activity monitoring system using the SPINE framework. In Proceedings of the 3rd International Conference on Pervasive Computing Technologies for Healthcare, Pervasive Health 2009, pages 1-8. IEEE Press, April 2009.
  • Step-counting based on single waist-worn inertial sensor – Implementation based on SPINE1
    • G. Fortino, R. Gravina, W. Li, C. Ma, Using Cloud-assisted Body Area Networks to Track People Physical Activity in Mobility, In Proc. of the 10th International Conference on Body Area Networks (BodyNets 2015). Sydney, Australia, Sep 2015.
  • Energy expenditure based on activity counts and single waist-worn inertial sensor – Implementation based on SPINE1
  • Body joints rehabilitation assessment (flexion and torsion angles monitoring) based on body-worn inertial sensors – Implementation based on SPINE1
    • G. Fortino, R. Gravina, A Cloud-Assisted Wearable System for Physical Rehabilitation, In ICTs for Improving Patients Rehabilitation Research Techniques, Vol. 515, pp. 168-182, Nov 2015.
  • Mental stress detection based on time-domain heart rate variability analysis – Implementation based on SPINE1
    • A. Andreoli, R. Gravina, R. Giannantonio, P. Pierleoni, and G. Fortino. SPINE-HRV: a BSN-based toolkit for heart rate variability analysis in the time-domain. Wearable and Autonomous Biomedical Devices and Systems: New issues and Characterization – Lecture Notes on Electrical Engineering, 75:369-389, 2010.
  • Cardiac Defense Response detection – Implementation based on SPINE1
    • R. Gravina, G. Fortino. Automatic methods for the detection of accelerative cardiac defense response, IEEE Transaction on Affective Computing, 7 (3), pp. 286–298, 2016.
  • Gait Analysis based on Hidden Markov Models – Implementation using Virtual Sensors based on SPINE2
    • N. Raveendranathan et al., “From Modeling to Implementation of Virtual Sensors in Body Sensor Networks,” in IEEE Sensors Journal, vol. 12, no. 3, pp. 583-593, March 2012, doi: 10.1109/JSEN.2011.2121059.
  • Action Recognition based on Template-matching and boosting approaches – Implementation based on SPINE2
    • H. Ghasemzadeh, P. Panuccio, S. Trovato, G. Fortino and R. Jafari, “Power-Aware Activity Monitoring Using Distributed Wearable Sensors,” in IEEE Transactions on Human-Machine Systems, vol. 44, no. 4, pp. 537-544, Aug. 2014, doi: 10.1109/THMS.2014.2320277.
  • Activity recognition with autonomic noise filter removal algorithm – Implementation based on SPINE-*
    • Stefano Galzarano, Giancarlo Fortino, Antonio Liotta: Embedded self-healing layer for detecting and recovering sensor faults in body sensor networks. SMC 2012: 2377-2382
  • Cooperative multi-sensor data fusion for handshake detection based on local embedded DT classifiers and global cooperative classification fusion – Implementation based on C-SPINE
    • Giancarlo Fortino, Stefano Galzarano, Raffaele Gravina, Wenfeng Li: A framework for collaborative computing and multi-sensor data fusion in body sensor networks. Inf. Fusion 22: 50-70 (2015)
  • D-S evidence theory and multi-sensor data fusion for human postures recognition – Implementation based on SPINE
    • Wenfeng Li, Junrong Bao, Xiuwen Fu, Giancarlo Fortino, Stefano Galzarano: Human Postures Recognition Based on D-S Evidence Theory and Multi-sensor Data Fusion. CCGRID 2012: 912-917
  • Human motion capture based on quaternion navigation algorithm – Implementation based on SPINE
    • Jie li, Zhelong Wang, Hongyu Zhao, Raffaele Gravina, Giancarlo Fortino, Yongmei Jiang, Kai Tang, (2017) Networked Human Motion Capture System Based on Quaternion Navigation, BODYNETS, EAI, DOI: 10.4108/eai.15-12-2016.2267544
  • Multi-Sensor Fusion algorithm and dual-gait analysis for Heading Drift Reduction for Foot-Mounted Inertial Navigation System: “A Kalman-type filter with one time update and two measurement updates is developed to fuse the velocity and position observations at foot and person levels”- Implementation based on SPINE
    • H. Zhao et al., “Heading Drift Reduction for Foot-Mounted Inertial Navigation System via Multi-Sensor Fusion and Dual-Gait Analysis,” in IEEE Sensors Journal, vol. 19, no. 19, pp. 8514-8521, 1 Oct.1, 2019, doi: 10.1109/JSEN.2018.2866802.
  • A new algorithm for ECG-based biometric authentication that is considered highly promising in terms of user identification for smart healthcare systems, was proposed. The developed PEA (Parallel ECG-based Authentication) method is based on: fiducial- and non-fiducial-based ECG feature extraction and efficient parallel ECG pattern recognition framework.
    • Yin Zhang, Raffaele Gravina, Huimin Lu, Massimo Villari, Giancarlo Fortino: PEA: Parallel electrocardiogram-based authentication for smart healthcare systems. J. Netw. Comput. Appl. 117: 10-16 (2018)
  • A universal framework for sensor combination feature subset (SCFS) selection is proposed. In SCFS selection framework, the number of sensors can be reduced by using the feature selection method – The framework is really implementable atop BSNs using SPINE2
    • Wang, J., Wang, Z., Qiu, S., Xu, J., Zhao, H., Fortino, G., Habib, M. A selection framework of sensor combination feature subset for human motion phase segmentation (2021) Information Fusion, 70, pp. 1-11. DOI: 10.1016/j.inffus.2020.12.009
  • Multi-sensor data fusion algorithm for gait identification in older adults: “The proposed arbitration-based score level fusion method can improve the recognition rate” – Design based on SPINE
    • Fangmin Sun, Weilin Zang, Raffaele Gravina, Giancarlo Fortino, Ye Li: Gait-based identification for elderly users in wearable healthcare systems. Inf. Fusion 53: 134-144 (2020)
  • Sensor fusion to utilize the gross motor function of CP children. An evaluation method for hippotherapy based on BSN. A method of human motion capture by traversing the kinematic chains. Lower limb gait analysis to evaluate the rehabilitation of CP children. Evaluation of upper limb balance ability based on trunk posture. System implementation is based on SPINE.
    • Li, J., Wang, Z., Qiu, S., Zhao, H., Wang, J., Shi, X., Liang, B., Fortino, G. Multi-body sensor data fusion to evaluate the hippotherapy for motor ability improvement in children with cerebral palsy (2021) Information Fusion, 70, pp. 115-128. DOI: 10.1016/j.inffus.2021.01.002
  • This paper puts forward the ambitious objective to employ multiple wearable Electromyography (EMG) sensors for gait abnormalities detection. Our proposed approach uses eight wireless EMG sensors attached with skin electrodes on four muscles (i.e., Tibialis Anterior, Peroneus Longus, Gas-trocnemius, and Rectus Femoris) per each leg to measure the muscle response during walking activity. In the recognition stage, both meta-features with SVM and Bidirectional Long Short-Term Machine (BiLSTM) are exploited for gait abnormalities recognition from raw EMG data, Discrete Wavelet Transform (DWT) coefficients, and the reconstructed EMG signals, respectively. Currently the design of the real system is based on SPINE.
    • Y. Guo, R. Gravina, X. Gu, G. Fortino and G. -Z. Yang, “EMG-based Abnormal Gait Detection and Recognition,” 2020 IEEE International Conference on Human-Machine Systems (ICHMS), Rome, Italy, 2020, pp. 1-6, doi: 10.1109/ICHMS49158.2020.9209449.
  • Use emotion-relevant activities as a new information source to support emotion recognition. Generalised sequence feature-based technique to recognise postural activities. Sensor- and feature-level fusion to jointly process pressure and inertial data. SPINE was used to collect data from the smart cushion.
    • Raffaele Gravina, Qimeng Li: Emotion-relevant activity recognition based on smart cushion using multi-sensor fusion. Inf. Fusion 48: 1-10 (2019)
  • The paper also proposes an intelligent data fusion algorithm for eye movement classification whose input vector is represented by the first three principal components. Adaptive neuro fuzzy inference system (ANFIS) is built to classify and recognize the eye movements (Up, Down, Left, and Right). Furthermore, experiments have demonstrated that ANFIS algorithm achieves 90% recognition accuracy of such eye movements. This work demonstrates that soft multi-functional electronic skin integrated with data fusion algorithm can successfully solve the eye movement tracking problem, with significant impact in safety driving and wearable electronics. The system design was carried out using SPINE methods.
    • Wentao Dong, Lin Yang, Raffaele Gravina, Giancarlo Fortino, ANFIS fusion algorithm for eye movement recognition via soft multi-functional electronic skin, Information Fusion, 2021. to appear.