Publications
204 results found
Wang H, Feng R, Leung C-S, et al., 2023, A Globally Stable LPNN Model for Sparse Approximation, IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, Vol: 34, Pages: 5218-5226, ISSN: 2162-237X
- Author Web Link
- Cite
- Citations: 1
Scalzo B, Stankovic L, Dakovic M, et al., 2023, A class of doubly stochastic shift operators for random graph signals and their boundedness, NEURAL NETWORKS, Vol: 158, Pages: 83-88, ISSN: 0893-6080
- Author Web Link
- Cite
- Citations: 1
Wang H, Feng R, Leung C-S, et al., 2022, A Lagrange Programming Neural Network Approach with an <i>l</i><sub>0</sub>-Norm Sparsity Measurement for Sparse Recovery and Its Circuit Realization, MATHEMATICS, Vol: 10
- Author Web Link
- Cite
- Citations: 1
Bugallo MF, Constantinides AG, Mandic DP, et al., 2021, Innovation Starts With Education, IEEE SIGNAL PROCESSING MAGAZINE, Vol: 38, Pages: 11-13, ISSN: 1053-5888
- Author Web Link
- Cite
- Citations: 1
Dees BS, Xu YL, Constantinides AG, et al., 2021, Graph Theory for Metro Traffic Modelling, International Joint Conference on Neural Networks (IJCNN), Publisher: IEEE, ISSN: 2161-4393
Shi Z, Wang H, Leung C-S, et al., 2020, Robust ellipse fitting based on Lagrange programming neural network and locally competitive algorithm, NEUROCOMPUTING, Vol: 399, Pages: 399-413, ISSN: 0925-2312
- Author Web Link
- Cite
- Citations: 9
Stankovic L, Mandic D, Dakovic M, et al., 2020, Data Analytics on Graphs Part I: Graphs and Spectra on Graphs, FOUNDATIONS AND TRENDS IN MACHINE LEARNING, Vol: 13, Pages: 1-157, ISSN: 1935-8237
- Author Web Link
- Cite
- Citations: 19
Stankovic L, Mandic D, Dakovic M, et al., 2020, Data Analytics on Graphs Part III: Machine Learning on Graphs, from Graph Topology to Applications, FOUNDATIONS AND TRENDS IN MACHINE LEARNING, Vol: 13, Pages: 332-530, ISSN: 1935-8237
- Author Web Link
- Cite
- Citations: 21
Stankovic L, Mandic D, Dakovic M, et al., 2020, Data Analytics on Graphs Part II: Signals on Graphs, FOUNDATIONS AND TRENDS IN MACHINE LEARNING, Vol: 13, Pages: 158-331, ISSN: 1935-8237
- Author Web Link
- Cite
- Citations: 15
Dees BS, Stankovic L, Constantinides AG, et al., 2020, PORTFOLIO CUTS: A GRAPH-THEORETIC FRAMEWORK TO DIVERSIFICATION, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Publisher: IEEE, Pages: 8454-8458, ISSN: 1520-6149
- Author Web Link
- Cite
- Citations: 3
Stankovic L, Dakovic M, Mandic D, et al., 2020, A LOW-DIMENSIONALITY METHOD FOR DATA-DRIVEN GRAPH LEARNING, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Publisher: IEEE, Pages: 5340-5344, ISSN: 1520-6149
- Author Web Link
- Cite
- Citations: 1
Kanna S, von Rosenberg W, Goverdovsky V, et al., 2018, Bringing Wearable Sensors into the Classroom: A Participatory Approach, IEEE SIGNAL PROCESSING MAGAZINE, Vol: 35, Pages: 110-+, ISSN: 1053-5888
Hemakom A, Chanwimalueang T, Carrion A, et al., 2016, Financial Stress Through Complexity Science, IEEE Journal of Selected Topics in Signal Processing, Vol: 10, Pages: 1112-1126, ISSN: 1932-4553
Abstract:Financial markets typically undergo periods of prosperity followed by periods of stagnation, and this undulation makes it challenging to maintain market efficiency. The efficient market hypothesis (EMH) states that there exist differences in structural complexity in security prices between regular and abnormal situations. Yet, despite a clear link between market acceleration (cf. recession in security prices) and stress in physical systems, indices of financial stress still have significant scope for further development. The overarching aim of this work is therefore to determine the characteristics of financial indices related to financial stress, and to establish a robust metric for the extent of such `stress'. This is achieved based on intrinsic multiscale analysis which quantifies the so called complexity-loss hypothesis in the context of financial stress. The multiscale sample entropy and our proposed Assessment of Latent Index of Stress methods have successfully assessed financial stress, and have served as a measure to establish an analogy between transitions from `normal' (relaxed) to `abnormal' (stressed) financial periods with the sympatho-vagal balance in humans. Four major stock indices of the US economy over the past 25 years are considered: (i) Dow Jones Industrial Average, (ii) NASDAQ Composite, (iii) Standard & Poor's 500, and (iv) Russell 2000, together with FTSE 100, CAC 40 and exchange rates. Our findings support the EMH theory and reveal high stress for both the periods of Internet bubble burst and sub-prime mortgage crisis.
Antoniou ZC, Panayides AS, Pantziaris M, et al., 2016, Dynamic Network Adaptation for Real-Time Medical Video Communication, 14th Mediterranean Conference on Medical and Biological Engineering and Computing (MEDICON), Publisher: SPRINGER, Pages: 1093-1098, ISSN: 1680-0737
The wider adoption of mHealth video communication systems in standard clinical practice requires adequate levels of clinical video quality to support reliable diagnosis. The latter dictates that real-time adaptation to time-varying wireless networks’ state to guarantee clinically acceptable performance throughout the streaming session, while conforming to device capabilities for supporting real-time encoding. In this study we propose a multi-objective optimization framework that jointly maximizes the encoded video’s quality while minimizing bitrate demands and encoding time. Experimental investigation shows that the proposed framework can provide for efficient real-time adaptation at a Group of Pictures (GOP) level, demonstrating significant gains over static approaches.
Feng R-B, Leung C-S, Constantinides AG, 2016, LCA based RBF training algorithm for the concurrent fault situation, Neurocomputing, Vol: 191, Pages: 341-351, ISSN: 1872-8286
Mandic DP, Kanna S, Constantinides AG, 2015, On the Intrinsic Relationship Between the Least Mean Square and Kalman Filters, IEEE SIGNAL PROCESSING MAGAZINE, Vol: 32, Pages: 117-122, ISSN: 1053-5888
- Author Web Link
- Cite
- Citations: 32
Thanthawaritthisai T, Tobar F, Constantinides AG, et al., 2015, THE WIDELY LINEAR QUATERNION RECURSIVE TOTAL LEAST SQUARES, 40th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Publisher: IEEE, Pages: 3357-3361, ISSN: 1520-6149
Han Z-F, Leung C-S, So HC, et al., 2015, Non-Line-of-Sight Mitigation via Lagrange Programming Neural Networks in TOA-Based Localization, 22nd International Conference on Neural Information Processing (ICONIP), Publisher: SPRINGER INTERNATIONAL PUBLISHING AG, Pages: 190-197, ISSN: 0302-9743
- Author Web Link
- Cite
- Citations: 2
Leung C-S, Sum J, Constantinides AG, 2014, Recurrent networks for compressive sampling, NEUROCOMPUTING, Vol: 129, Pages: 298-305, ISSN: 0925-2312
- Author Web Link
- Cite
- Citations: 12
Leung CS, Sum J, So HC, et al., 2014, Lagrange programming neural networks for time-of-arrival-based source localization, NEURAL COMPUTING & APPLICATIONS, Vol: 24, Pages: 109-116, ISSN: 0941-0643
- Author Web Link
- Cite
- Citations: 26
Feng R, Leung C-S, Constantinides AG, 2014, An Analog Network Approach to train RBF Networks based on Sparse Recovery, 19th International Conference on Digital Signal Processing (DSP), Publisher: IEEE, Pages: 903-908, ISSN: 1546-1874
Tobar FA, Orchard ME, Mandic DP, et al., 2014, Estimation of Financial Indices Volatility Using a Model with Time-Varying Parameters, IEEE Conference on Computational Intelligence for Financial Engineering and Economics (CIFEr), Publisher: IEEE, Pages: 318-324, ISSN: 2380-8454
- Author Web Link
- Cite
- Citations: 3
Chobey DK, Lim YC, Constantinides AG, 2014, Steady-State Comparative Performance Evaluation of Piloted Adaptive Notch Filter, 19th International Conference on Digital Signal Processing (DSP), Publisher: IEEE, Pages: 316-320, ISSN: 1546-1874
- Author Web Link
- Cite
- Citations: 3
Panayides A, Pattichis MS, Loizou C, et al., 2014, An Effective Ultrasound Video Communication System Using Despeckle Filtering and HEVC, Biomedical and Health Informatics, IEEE Journal of, Vol: PP, Pages: 1-8, ISSN: 2168-2194
Lim YC, Huang C, Li G, et al., 2013, Error Spectrum Shaping Approach for Lattice Filter Roundoff Noise Reduction, IEEE International Symposium on Circuits and Systems (ISCAS), Publisher: IEEE, Pages: 85-88, ISSN: 0271-4302
Panayides AS, Pattichis MS, Constantinides AG, et al., 2013, M-health medical video communication systems: An overview of design approaches and recent advances, Pages: 7253-7256-7253-7256, ISSN: 1557-170X
The emergence of the new, High Efficiency Video Coding (HEVC) standard, combined with wide deployment of 4G wireless networks, will provide significant support toward the adoption of mobile-health (m-health) medical video communication systems in standard clinical practice. For the first time since the emergence of m-health systems and services, medical video communication systems can be deployed that can rival the standards of in-hospital examinations. In this paper, we provide a thorough overview of today’s advancements in the field, discuss existing approaches, and highlight the future trends and objectives.
Rebollo-Neira L, Bowley J, Constantinides AG, et al., 2012, Self-contained encrypted image folding, PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, Vol: 391, Pages: 5858-5870, ISSN: 0378-4371
- Author Web Link
- Cite
- Citations: 10
Zhang X, Banavar MK, Willerton M, et al., 2012, Performance comparison of localization techniques for sequential WSN discovery
In this paper, the performance of different localization algorithms are compared in the context of the sequential Wireless Sensor Network (WSN) discovery problem. Here, all sensor nodes are at unknown locations except for a very small number of so called anchor nodes at known locations. The locations of nodes are sequentially estimated such that when the location of a given node is found, it may be used to localize others. The underlying performance of such an approach is largely dependent upon the localization technique employed. In this paper, several well-known localization techniques are presented using a unified notation. These methods are time of arrival (TOA), time difference of arrival (TDOA), received signal strength (RSS), direction of arrival (DOA) and large aperture array (LAA) localization. The performance of a sequential network discovery process is then compared when using each of these localization algorithms. These algorithms are implemented in the Java-DSP software package as part of a localization toolbox.
Panayides A, Antoniou Z, Pattichis MS, et al., 2012, High efficiency video coding for ultrasound video communication in m-health systems., Annu Int Conf IEEE Eng Med Biol Soc, Vol: 2012, Pages: 2170-2173
Emerging high efficiency video compression methods and wider availability of wireless network infrastructure will significantly advance existing m-health applications. For medical video communications, the emerging video compression and network standards support low-delay and high-resolution video transmission, at the clinically acquired resolution and frame rates. Such advances are expected to further promote the adoption of m-health systems for remote diagnosis and emergency incidents in daily clinical practice. This paper compares the performance of the emerging high efficiency video coding (HEVC) standard to the current state-of-the-art H.264/AVC standard. The experimental evaluation, based on five atherosclerotic plaque ultrasound videos encoded at QCIF, CIF, and 4CIF resolutions demonstrates that 50% reductions in bitrate requirements is possible for equivalent clinical quality.
Willerton M, Banavar M, Zhang X, et al., 2012, Sequential Wireless Sensor Network Discovery Using Wide Aperture Array Signal Processing, EUSIPCO 2012
In this paper, a novel wireless sensor network discovery algorithm is presented which estimates the position of a large number of low powered, randomly distributed sensor nodes. Initially, all nodes are at unknown locations except for a smallnumber which are termed the “anchor” nodes. The remaining nodes are to be located as part of the discovery procedure. As the locations of sensor nodes are estimated, they can be used in the localization of other nodes. Transmitting nodes in unknown locations are localized in a decentralized manner by using a set of receiving sensor nodes at known or estimated locations within its coverage area. This set of nodes forms an array which is used for localization. Initially a coarse localisation of all nodes is performed to identify their approximate positions. A fine grained localization procedure then follows for refinement. This paper will focus on the coarse localizationapproach. Simulations demonstrate the effectiveness of the proposed method.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.