-
[show abstract]
[hide abstract]
ABSTRACT: This chapter describes the application of neural networks to the prediction of “paper curl”, an important quality metric in
the papermaking industry. In particular we address the issue of reliability in neural network training and prediction. Model
combination is used to compensate for the limitations of non-linear optimization algorithms used for neural network training.
In addition, confidence measures are used to characterize prediction uncertainty. Reliability enhancement though model combination
enables training to be automated. The provision of a confidence measure along with the prediction facilitates the user in
knowing whether to trust the prediction or not.
06/2011: pages 147-175;
-
Neurocomputing 01/2011; 74:930-940. · 1.58 Impact Factor
-
T B Tang,
S Smith,
B W Flynn,
J T M Stevenson,
A M Gundlach,
H M Reekie, A F Murray,
D Renshaw,
B Dhillon,
A Ohtori,
Y Inoue,
J G Terry,
A J Walton
[show abstract]
[hide abstract]
ABSTRACT: A wireless power transfer and communication system based on near-field inductive coupling has been designed and implemented. The feasibility of using such a system to remotely control drug release from an implantable drug delivery system is addressed. The architecture of the wireless system is described and the signal attenuation over distance in both water and phosphate buffered saline is studied. Additionally, the health risk due to exposure to radio frequency (RF) radiation is examined using a biological model. The experimental results demonstrate that the system can trigger the release of drug within 5 s, and that such short exposure to RF radiation does not produce any significant (<or= 1 degrees C) heating in the biological model. The conclusion of the work is that this system could replace a chemical battery in an implantable system, eliminating the risks associated with battery failure and leakage and also allowing more compact designs for applications such as drug delivery.
IET Nanobiotechnology 10/2008; 2(3):72-9. · 1.83 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: 1/f noise and random telegraph signal (RTS) noise are increasingly dominant sources of low-frequency noise as the MOSFET enters the nanoscale regime. In this study, 1/f noise and RTS noise in the n-channel MOSFET are modelled in the time domain for efficient implementation in transient circuit simulation. A technique based on sum-of-sinusoids models 1/f noise while a Monte Carlo based technique is used to generate RTS noise. Low-frequency noise generated using these models exhibits the correct form of noise characteristics as predicted by theory, with noise parameters from standard 0.35-mum and 35-nm CMOS technology. Implementation of the time-domain model in SPICE shows the utility of the noisy MOSFET model in simulating the effect of low-frequency noise on the operation of deep-submicrometer analog integrated circuits.
Circuits and Systems I: Regular Papers, IEEE Transactions on 03/2008; · 1.97 Impact Factor
-
S Smith,
T B Tang,
J G Terry,
J T M Stevenson,
B W Flynn,
H M Reekie, A F Murray,
A M Gundlach,
D Renshaw,
B Dhillon,
A Ohtori,
Y Inoue,
A J Walton
[show abstract]
[hide abstract]
ABSTRACT: The development of an implantable system designed to deliver drug doses in a controlled manner over an extended time period is reported. Key performance parameters are the physical size, the power consumption and also the ability to perform wireless communications to enable the system to be externally controlled and interrogated. The system has been designed to facilitate wireless power transfer, which is very important for miniaturisation as it removes the need for a battery.
IET Nanobiotechnology 11/2007; 1(5):80-6. · 1.83 Impact Factor
-
A.J. Walton,
J.T.M. Stevenson,
I. Underwood,
J.G. Terry,
S. Smith,
W. Parkes,
C. Dunare,
H. Lin,
Y. Li,
R. Henderson,
D. Renshaw,
K. Muir,
M. Desmulliez,
D. Flynn,
M.J. MacIntosh,
W.S. Holland, A.F. Murray,
T.B. Tang,
A. Bunting,
A.M. Gundlach
Micro Electro-Mechanical Systems, 2007. MEMS Technology. 2007 IET Seminar on; 05/2007
-
A. J. Walton,
J. T. M. Stevenson,
I. Underwood,
J. G. Terry,
S. Smith,
W. Parkes,
C. Dunare,
H. Lin,
Y. Li,
R. Henderson,
D. Renshaw,
K. Muir,
M. Desmulliez,
D. Flynn,
M. J. MacIntosh,
W. S. Holland, A. F. Murray,
T. B. Tang,
A. Bunting,
A. M. Gundlach
Micro Electro-Mechanical Systems, 2007. MEMS Technology. 2007 IET Seminar on; 01/2007
-
L. Wang,
N. Aydin,
A. Astaras,
M. Ahmadian,
P.A. Hammond,
T.B. Tang,
E. Johannessen,
T. Arslan,
S.P. Beaumont,
B.W. Flynn, A.F. Murray,
J.M. Cooper,
D.R.S. Cumming
[show abstract]
[hide abstract]
ABSTRACT: Recent years have seen the rapid development of microsensor technology, system on chip design, wireless technology and ubiquitous computing. When assembled into a complex microsystem the technologies become powerful tools in medical diagnostics, environmental monitoring and personal connectivity. In this paper we describe the demonstration of a silicon chip that has all the attributes required of a microsystem for use in these applications. The design methodology we have employed is a variant of the system on chip approach whereby many intellectual property blocks are integrated at a high level in the design flow. Our intellectual property blocks include the analogue sensor instrumentation for temperature and pH, a data multiplexing and conversion module, a digital platform based around an 8-bit microcontroller, data encoding for spread-spectrum wireless transmission and a RF section requiring very few off-chip components. The chip has been fully evaluated and tested by connection to external sensors. Each block has well defined interfaces so that they can be easily reused in future designs targeted to different applications
Circuits and Systems, 2006. ISCAS 2006. Proceedings. 2006 IEEE International Symposium on; 06/2006
-
T.B. Tang,
S Smith,
B.W. Flynn,
J T M Stevenson,
A M Gundlach,
H.M. Reekie, A.F. Murray,
D Renshaw,
B Dhillon,
A Ohtori,
Y Inoue,
J.G. Terry,
A J Walton
01/2006;
-
L. Wang,
Nizamettin Aydin,
A. Astaras,
M. Ahmadian,
P. A. Hammond,
T. B. Tang,
Erik A. Johannessen,
Tughrul Arslan,
S. P. Beaumont,
B. W. Flynn, A. F. Murray,
Jonathan M. Cooper,
David R. S. Cumming
International Symposium on Circuits and Systems (ISCAS 2006), 21-24 May 2006, Island of Kos, Greece; 01/2006
-
[show abstract]
[hide abstract]
ABSTRACT: The authors consider design issues associated with the use of high-frequency inductive coupling, in the context of miniaturised, embedded electronic systems in medical diagnosis, environmental monitoring and other industrial applications. Recent developments in system-on-chip and lab-on-a-chip technologies have made the implementation of such miniaturised systems feasible, and pose an interesting set of problems with respect to low-power, short-range wireless communications. The design of a compact transmitter that maximises the magnetic component of the field is discussed and some early results are presented.
IEE Proceedings - Communications 05/2005; · 0.32 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: We have developed an integrated circuit microsystem instrument using a design methodology akin to that for system-on-chip microelectronics. The microsystem is optimised for low-power gastrointestinal telemetry applications and includes mixed-signal sensor circuits, programmable digital system, a feedback clock control loop and RF circuits that were integrated on a 5 mm × 5 mm silicon chip using a 0.6 μm, 3 V CMOS process. Unintended signal coupling between circuit components has been investigated and current injection into sensitive instrumentation nodes has been minimised. Tests show that the wireless instrument-on-chip worked as intended.
Engineering in Medicine and Biology Society, 2004. IEMBS '04. 26th Annual International Conference of the IEEE; 10/2004
-
[show abstract]
[hide abstract]
ABSTRACT: Spike-timing dependent synaptic plasticity (STDP) is a form of plasticity driven by precise spike-timing differences between presynaptic and postsynaptic spikes. Thus, the learning rules underlying STDP are suitable for learning neuronal temporal phenomena such as spike-timing synchrony. It is well known that weight-independent STDP creates unstable learning processes resulting in balanced bimodal weight distributions. In this paper, we present a neuromorphic analog very large scale integration (VLSI) circuit that contains a feedforward network of silicon neurons with STDP synapses. The learning rule implemented can be tuned to have a moderate level of weight dependence. This helps stabilise the learning process and still generates binary weight distributions. From on-chip learning experiments we show that the chip can detect and amplify hierarchical spike-timing synchrony structures embedded in noisy spike trains. The weight distributions of the network emerging from learning are bimodal.
IEEE Transactions on Neural Networks 10/2004; 15(5):1296-1304. · 2.95 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: We have mapped the contrastive divergence learning scheme of the product of experts (PoE) onto electrical circuits. The issues raised during that hardware translation are discussed in This work and some circuits presenting our solutions are described. The entire learning rule is implemented in mixed-signal VLSI on a 0.6 μm CMOS process. Chips results validating our approach and methodology are also presented.
Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on; 08/2004
-
E.A. Johannessen,
Lei Wang,
Li Cui,
Tong Boon Tang,
M. Ahmadian,
A. Astaras,
S.W.J. Reid,
P.S. Yam, A.F. Murray,
B.W. Flynn,
S.P. Beaumont,
D.R.S. Cumming,
J.M. Cooper
[show abstract]
[hide abstract]
ABSTRACT: A novel microelectronic "pill" has been developed for in situ studies of the gastro-intestinal tract, combining microsensors and integrated circuits with system-level integration technology. The measurement parameters include real-time remote recording of temperature, pH, conductivity, and dissolved oxygen. The unit comprises an outer biocompatible capsule encasing four microsensors, a control chip, a discrete component radio transmitter, and two silver oxide cells (the latter providing an operating time of 40 h at the rated power consumption of 12.1 mW). The sensors were fabricated on two separate silicon chips located at the front end of the capsule. The robust nature of the pill makes it adaptable for use in a variety of environments related to biomedical and industrial applications.
IEEE Transactions on Biomedical Engineering 04/2004; · 2.28 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: An adaptive stochastic classifier based on a simple, novel neural architecture--the Continuous Restricted Boltzmann Machine (CRBM) is demonstrated. Together with sensors and signal conditioning circuits, the classifier is capable of measuring and classifying (with high accuracy) the H+ ion concentration, in the presence of both random noise and sensor drift. Training on-line, the stochastic classifier is able to overcome significant drift of real incomplete sensor data dynamically. As analogue hardware, this signal-level sensor fusion scheme is therefore suitable for real-time analysis in a miniaturised multisensor microsystem such as a Lab-in-a-Pill (LIAP).
IEE Proceedings - Nanobiotechnology 03/2004; 151(1):28-34. · 1.82 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: This paper considers design of a miniature transmitter operating with near-field inductive coupling, in the context of embedded electronic systems in medical diagnosis, environmental monitoring, and other industrial applications. Recent developments in system-on-chip and lab-on-a-chip technologies made the implementation of such miniaturized systems feasible, and pose an interesting set of problems with respect to low-power, short-range wireless communications. The design of a compact transmitter with a magnetic antenna is discussed and some early results are presented.
Engineering in Medicine and Biology Society, 2003. Proceedings of the 25th Annual International Conference of the IEEE; 10/2003
-
[show abstract]
[hide abstract]
ABSTRACT: Developments in system-on-chip and wireless technologies have led to complex electronic systems to be miniaturized to size of ingestible capsule and implantable microsystems. Inevitably such miniaturized complex systems impose some constraints on the case of an ingestible diagnostic capsule. It is desirable that system be wireless, programmable, and reusable. In this paper, we describe a wireless interface link developed for such an ingestible microsystem. It is programmable and directly controlled by the on-chip microcontroller. It is also suitable for developing complex communication protocols for conveying the data to a remote basestation. At the heart of the system lie a direct sequence spread spectrum encoder.
Engineering in Medicine and Biology Society, 2003. Proceedings of the 25th Annual International Conference of the IEEE; 10/2003
-
[show abstract]
[hide abstract]
ABSTRACT: The authors introduce a continuous stochastic generative model that can model continuous data, with a simple and reliable training algorithm. The architecture is a continuous restricted Boltzmann machine, with one step of Gibbs sampling, to minimise contrastive divergence, replacing a time-consuming relaxation search. With a small approximation, the training algorithm requires only addition and multiplication and is thus computationally inexpensive in both software and hardware. The capabilities of the model are demonstrated and explored with both artificial and real data.
IEE Proceedings - Vision Image and Signal Processing 07/2003;
-
Lei Wang,
E.A. Johannessen,
Li Cui,
C. Ramsay,
Tong Boon Tang,
M. Ahmadian,
A. Astaras,
P.W. Dickman,
J.M. Cooper, A.F. Murray,
B.W. Flynn,
S.P. Beaumont,
D.R.S. Cumming
[show abstract]
[hide abstract]
ABSTRACT: The introduction of microsystem and Laboratory-in-a-Pill technologies into medical diagnostics has been a growing field over several decades, where low form factor can significantly improve device access and patient comfort. Similarly, remote medicine and monitoring networks have become more important and popular. In this paper, we present our results on research towards a wireless microsystem network that can deliver analytical data from microsystems distributed in one or more patients' gastrointestinal tracts to a remote monitoring network. We believe that the combination of microsystem and network technologies will greatly benefit future medical research.
TRANSDUCERS, Solid-State Sensors, Actuators and Microsystems, 12th International Conference on, 2003; 07/2003