Project

SENSIBLE

Goal: The goal of this project is to develop a novel integrated decision support mechanism embedding intelligent sensing, communications and data processing methodology for improving sustainability of smart buildings through new insights, approaches and technologies for acquisition, communications, and extraction of useful information from the sheer volume of sensed data in the built environment.
http://sensible.eee.strath.ac.uk/index.html

Updates
0 new
11
Recommendations
0 new
4
Followers
0 new
12
Reads
1 new
312

Project log

Vladimir Stankovic
added an update
Three research positions available for PhD students as part of an EU ITN funded project. The successful candidates will work on explainable AI for smart home technologies. Annual salary in the range of EUR60,000.
 
Vladimir Stankovic
added an update
New findings of SENSIBLE team researchers showed that a traditional federated learning approach of aggregating trained parameters is not optimal. More details in a joint paper by Tongji, University of Strathclyde, and University of Novi Sad researchers:
 
Vladimir Stankovic
added an update
Three papers accepted at IEEE ICASSP-2019 Conference, including joint work between Strathclyde and PanonIT on NILM and Strathclyde and NII on robust deep graph learning. The work of Strathclyde and Tongji on graph signal processing will also be presented.
 
Vladimir Stankovic
added 6 research items
Machine-type communications and large-scale information processing architectures are among key (r)evolutionary enhancements of emerging fifth-generation (5G) mobile cellular networks. Massive data acquisition and processing will make 5G network an ideal platform for large-scale system monitoring and control with applications in future smart transportation, connected industry, power grids, etc. In this work, we investigate a capability of such a 5G network architecture to provide the state estimate of an underlying linear system from the input obtained via large-scale deployment of measurement devices. Assuming that the measurements are communicated via densely deployed cloud radio access network (C-RAN), we formulate and solve the problem of estimating the system state from the set of signals collected at C-RAN base stations. Our solution, based on the Gaussian Belief-Propagation (GBP) framework, allows for large-scale and distributed deployment within the emerging 5G information processing architectures. The presented numerical study demonstrates the accuracy, convergence behavior and scalability of the proposed GBP-based solution to the large-scale state estimation problem.
Semi-supervised binary classifier learning is a fundamental machine learning task where only partial binary labels are observed, and labels of the remaining data need to be interpolated. Leveraging on the advances of graph signal processing (GSP), recently binary classifier learning is posed as a signal restoration problem regularized using a graph smoothness prior, where the undirected graph consists of a set of vertices and a set of weighted edges connecting vertices with similar features. In this paper, we improve the performance of such a graph-based classifier by simultaneously optimizing the feature weights used in the construction of the similarity graph. Specifically, we start by interpolating missing labels by first formulating a boolean quadratic program with a graph signal smoothness objective, then relax it to a convex semi-definite program, solvable in polynomial time. Next, we optimize the feature weights used for construction of the similarity graph by reusing the smoothness objective but with a convex set constraint for the weight vector. The reposed convex but non-differentiable problem is solved via an iterative proximal gradient descent algorithm. The two steps are solved alternately until convergence. Experimental results show that our alternating classifier / graph learning algorithm outperforms existing graph-based methods and support vector machines with various kernels.
Vladimir Stankovic
added an update
Tutorial "Unlocking the potential of smart meter data via signal and information processing"  will be presented by V. Stankovic and L. Stankovic at IEEE ICASSP-2019, Brighton, UK, on May 13th 2019. See https://2019.ieeeicassp.org/program#tutorials for more details.
 
Vladimir Stankovic
added an update
SENSIBLE team work on energy disaggregation via Deep Learning presented at the EU NILM workshop in Duisburg on 2 October 2018 (the video of the presentation available at: http://www.nilm.eu).
 
Vladimir Stankovic
added an update
Two journal papers accepted this month:
1. L. Chen, S. Cheng, V. Stankovic, and L. Stankovic, “Shift-enabled graphs: Graphs where shift-invariant filters are representable as polynomials of shift operations,” IEEE Sig. Proc. Letters, June 2018, accepted (https://pure.strath.ac.uk/portal/en/publications/shift-enabled-graphs(55a95db8-5c3c-4a2b-808a-280185207916).html)
2.. D. Bajovic, K. He, D. Vukobratovic, L. Stankovic, and V. Stankovic, “ Optimal detection and error exponents for Hidden semi-Markov models ,” IEEE J. Sel. Topics in Sig. Proc., accepted
 
Lina Stankovic
added a research item
In digital signal processing, shift-invariant filters can be represented as a polynomial expansion of a shift operation,that is, the Z-transform representation. When extended to graph signal processing (GSP), this would mean that a shift-invariant graph filter can be represented as a polynomial of the adjacency (shift) matrix of the graph. However, the characteristic and minimum polynomials of the adjacency matrix must be identical for the property to hold. While it has been suggested that this condition might be ignored as it is always possible to find a polynomial transform to represent the original adjacency matrix by another adjacency matrix that satisfies the condition, this letter shows that a filter that is shift invariant in terms of the original graph may not be shift invariant anymore under the modified graph and vice versa. We introduce the notion of "shift-enabled graph" for graphs that satisfy the aforementioned condition, and present a concrete example of a graph that is not "shift-enabled" and a shift-invariant filter that is not a polynomial of the shift operation matrix. The result provides a deeper understanding of shift-invariant filters when applied in GSP and shows that further investigation of shift-enabled graphs is needed to make it applicable to practical scenarios.
Vladimir Stankovic
added a research item
Most current non-intrusive load monitoring (NILM) algorithms disaggregate one appliance at a time, remove the appliance contribution towards the total load, and then move on to the next appliance. On one hand, this is effective since it avoids multi-class classification, and analytical models for each appliance can be developed independently of other appliances, and thus potentially transferred to unseen houses that have different sets of appliances. On the other hand, however, these methods can significantly under/over estimate the total consumption since they do not minimise the difference between the measured aggregate readings and the sum of estimated individual loads. By considering this difference, we propose a post-processing approach for improving the accuracy of event-based NILM. We pose an optimisation problem to refine the original disaggregation result and propose a heuristic to solve a (combinatorial) boolean quadratic problem through relaxing zero-one constraint sets to compact zero-one intervals. We propose a method to set the regularization term, based on the appliance working power. We demonstrate high performance of the proposed post-processing method compared with the simulated annealing method and original disaggregation results, for three houses in the REFIT dataset using two state-of-the-art event-based NILM methods.
Vladimir Stankovic
added an update
SENSIBLE project output, " Post-processing for Event-based Non-intrusive Load Monitoring" was presented at International NILM Workshop 2018 http://nilmworkshop.org/2018/index.html
 
Vladimir Stankovic
added 2 research items
We study detection of random signals corrupted by noise that over time switch their values (states) from a finite set of possible values, where the switchings occur at unknown points in time. We model such signals by means of a random duration model that to each possible state assigns a probability mass function which controls the statistics of durations of that state occurrences. Assuming two possible signal states and Gaussian noise, we derive optimal likelihood ratio test and show that it has a computationally tractable form of a matrix product, with the number of matrices involved in the product being the number of process observations. Each matrix involved in the product is of dimension equal to the sum of durations spreads of the two states, and it can be decomposed as a product of a diagonal random matrix controlled by the process observations and a sparse constant matrix which governs transitions in the sequence of states. Using this result, we show that the Neyman-Pearson error exponent is equal to the top Lyapunov exponent for the corresponding random matrices. Using theory of large deviations, we derive a lower bound on the error exponent. Finally, we show that this bound is tight by means of numerical simulations.
Vladimir Stankovic
added an update
The SENSIBLE project is being presented at the Mathematics for Big Data Workshop (https://www.dmi.uns.ac.rs/mathbd/index.html).
 
Vladimir Stankovic
added a research item
Low-cost depth sensors, such as Microsoft Kinect, have potential for non-contact health monitoring that is robust to ambient lighting conditions. However, captured depth images typically suer from high acquisition noise, and hence processing them to estimate biometrics is difficult. In this paper, we propose to capture depth video of a human subject using Kinect 2.0 to estimate his/her heart rate and rhythm; as blood is pumped from the heart to circulate through the head, tiny oscillatory head motion due to Newtonian mechanics can be detected for periodicity analysis. Specifically, we first restore a captured depth video via a joint bit-depth enhancement / denoising procedure, using a graph-signal smoothness prior for regularization. Second, we track an automatically detected head region throughout the depth video to deduce 3D motion vectors. The detected vectors are fed back to the depth restoration module in a loop to ensure that the motion information in two modules are consistent, improving performance of both restoration and motion tracking. Third, the computed 3D motion vectors are projected onto its principal component for 1D signal analysis, composed of trend removal, band-pass filtering, and wavelet-based motion denoising. Finally, the heart rate is estimated via Welch power spectrum analysis, and the heart rhythm is computed via peak detection. Experimental results show accurate estimation of the heart rate and rhythm using our proposed algorithm as compared to rate and rhythm estimated by a portable oximeter.
Vladimir Stankovic
added an update
Project goal
The goal of this project is to develop a novel integrated decision support mechanism embedding intelligent sensing, communications and data processing methodology for improving sustainability of smart buildings through new insights, approaches and technologies for acquisition, communications, and extraction of useful information from the sheer volume of sensed data in the built environment.
Background and motivation
Buildings contribute over 40% of the total energy demand, where half of that is due to non-residential buildings. The increase in working population, hours spent in offices, and growth in demand for building services and improved comfort, will escalate building energy demand. Thus, making buildings more energy efficient, is a key prerequisite for reaching the EU goals of 20% carbon footprint reduction by 2020. According to European Commission (EC) 2010 Energy Performance of Buildings Directive, improving the energy efficiency of buildings will decrease by 5-6% total EU energy consumption. All EU countries must set minimum energy performance requirements for new buildings, and for major renovation or retrofit work in old buildings. Based on EC 2012 Energy Efficiency Directive, EU countries must draw-up long-term national building renovation strategies. Information and communications technology (ICT) must play an essential role in reducing energy consumption of buildings and improving occupants’ comfort levels, through advanced sensing, simulation, modelling, analytical, and visualization tools.
Significant growth in the built environment raises the question of how to collect, interpret and use data to shape building services. The main challenges lie in the technology (e.g., volume, diversity and multi-dimensionality of data, computational and real-time sensing, communication and energy constraints) as well as in lack of demonstrated practice and business models. SENSIBLE will tackle increased diversity of data sources through an inter-disciplinary, inter-sectoral programme focused on novel integrated approaches for sensing, communicating and analysing large amount of complex and diverse data in smart buildings, underpinned by low-complexity battery-preserving hardware designs and implementations, and combining quantitative data (collected via physical sensors) and qualitative data (collected through surveys and user feedback).
To ensure best practice, SENSIBLE will use an iterative cohesive system design approach between end-users and industrial beneficiaries. Solutions will be tested using two building sites as testbeds, sensing the buildings and occupants in their usual daily routines, and demonstrating relevance of the integrated sensing, communications, and analytical methodologies. Key to SENSIBLE’s success is the sharing of knowledge, resources, methodology, equipment and data across disciplines and countries, applying the results across sectors, and feeding back findings and end-users experiences into technological designs and innovation.