Prapaporn Rattanatamrong

Towards Real-Time Distributed Signal Modeling for Brain-Machine Interfaces

New architectures for Brain-Machine Interface communication and control use mixture models for expanding rehabilitation capabilities of disabled patients. Here we present and test a dynamic data-driven (BMI) Brain-Machine Interface architecture that relies on multiple pairs of forward-inverse models to predict, control, and learn the trajectories of a robotic arm in a real-time closed-loop system. A method of window-RLS was used to compute the forward-inverse model pairs in real-time and a model switching mechanism based on reinforcement learning was used to test the ability to map neural activity to elementary behaviors. The architectures were tested with in vivodata and implemented using remote computing resources.

Cyber-Workstation for Computational Neuroscience

A Cyber-Workstation (CW) to study in vivo, real-time interactions between computational models and large-scale brain subsystems during behavioral experiments has been designed and implemented. The design philosophy seeks to directly link the in vivo neurophysiology laboratory with scalable computing resources to enable more sophisticated computational neuroscience investigation. The architecture designed here allows scientists to develop new models and integrate them with existing models (e.g. recursive least-squares regressor) by specifying appropriate connections in a block-diagram. Then, adaptive middleware transparently implements these user specifications using the full power of remote grid-computing hardware. In effect, the middleware deploys an on-demand and flexible neuroscience research test-bed to provide the neurophysiology laboratory extensive computational power from an outside source. The CW consolidates distributed software and hardware resources to support time-critical and/or resource-demanding computing during data collection from behaving animals. This power and flexibility is important as experimental and theoretical neuroscience evolves based on insights gained from data-intensive experiments, new technologies and engineering methodologies. This paper describes briefly the computational infrastructure and its most relevant components. Each component is discussed within a systematic process of setting up an in vivo, neuroscience experiment. Furthermore, a co-adaptive brain machine interface is implemented on the CW to illustrate how this integrated computational and experimental platform can be used to study systems neurophysiology and learning in a behavior task. We believe this implementation is also the first remote execution and adaptation of a brain-machine interface.

BMI cyberworkstation: Enabling dynamic data-driven brain-machine interface research through cyberinfrastructure

Dynamic data-driven brain-machine interfaces (DDDBMI) have great potential to advance the understanding of neural systems and improve the design of brain-inspired rehabilitative systems. This paper presents a novel cyberinfrastructure that couples in vivo neurophysiology experimentation with massive computational resources to provide seamless and efficient support of DDDBMI research. Closed-loop experiments can be conducted with in vivo data acquisition, reliable network transfer, parallel model computation, and real-time robot control. Behavioral experiments with live animals are supported with real-time guarantees. Offline studies can be performed with various configurations for extensive analysis and training. A Web-based portal is also provided to allow users to conveniently interact with the cyberinfrastructure, conducting both experimentation and analysis. New motor control models are developed based on this approach, which include recursive least square based (RLS) and reinforcement learning based (RLBMI) algorithms. The results from an online RLBMI experiment shows that the cyberinfrastructure can successfully support DDDBMI experiments and meet the desired real-time requirements.

Fuzzy scheduling of real-time ensemble systems

This paper addresses the problem of resource scheduling in real-time ensemble systems. An ensemble system uses multiple simple computational models (called “experts”) to produce its outputs. Real system requirements of ensemble systems (e.g., size, weight, power and cost constraints) often lead to limited availability of computational resources required to support concurrent execution of all their experts. In practical systems, uncertainties in execution time and resource utilization complicate even further the scheduling of these experts. We propose a fuzzy-logic feedback-based resource scheduler (FuzzyFES) that can provide real-time execution of all relevant experts while minimizing the impact of limited resources and uncertainties on the system performance. FuzzyFES consists of a fuzzy-logic controller (FZ), a task utilization adaptor (TUA) and a real-time task scheduler (RTS) working harmoniously in a closed loop with an ensemble system to be scheduled. By considering the uncertainties that may be present in the systems and deployment environments, FZ determines the total allowable CPU utilization for the ensemble system. TUA then calculates the amount of resource utilization to be allocated to each expert not exceeding the total allowable utilization. The assigned utilization from TUA ensures that critical experts achieve their best performance while guaranteeing minimum execution time needed by others. RTS creates a real-time schedule for the experts to execute on multiple processors according to the allotted utilization. Our performance evaluation of a case-study ensemble system with limited resources demonstrates that FuzzyFES can schedule experts to produce outputs closely similar to those of the same system with sufficient resources, although the limited-resource system has up to 40% fewer resources. The results also confirm FuzzyFESs efficiency and show that execution-time imprecision and occasional fluctuation of resource availability can be tolerated by at least 45% more than when the experts are scheduled in an open-loop manner.

Model development, testing and experimentation in a CyberWorkstation for Brain-Machine Interface research

The CyberWorkstation (CW) is an advanced cyber-infrastructure for Brain-Machine Interface (BMI) research. It allows the development, configuration and execution of BMI computational models using high-performance computing resources. The CWs concept is implemented using a software structure in which an “experiment engine” is used to coordinate all software modules needed to capture, communicate and process brain signals and motor-control commands. A generic BMI-model template, which specifies a common interface to the CWs experiment engine, and a common communication protocol enable easy addition, removal or replacement of models without disrupting system operation. This paper reviews the essential components of the CW and shows how templates can facilitate the processes of BMI model development, testing and incorporation into the CW. It also discusses the ongoing work towards making this process infrastructure independent.

Improved real-time scheduling of periodic tasks on multiprocessors

There is an increasing number of high‐performance periodic real‐time applications in areas such as control systems, autonomous robots and financial systems. This article presents a novel algorithm, called Notional Approximation for Balancing Load Residues (NABLR), for scheduling these applications on high‐performance computing resources. The algorithm utilizes a combination of task residual loads and runtime laxities to carefully plan task execution between two consecutive job arrivals, so that available resources can be fully utilized and avoid deadline misses as possible. The empirical study in our article presented at the 2011 International Conference on High Performance Computing and Simulation (HPCS) was further extended by including additional static task sets and a new adaptive task set generated by our motivating application in brain–machine interfaces, which simulates the control of movement of a prosthetic limb according to activities of input signals. Out of 25,000 task sets, NABLR can schedule up to 76% of the sets versus 43% by the best known efficient algorithm (named anticipating slack earliest deadline first until zero laxity [ASEDZL]), while incurring significantly smaller overheads than those of a known optimal algorithm (on average, 80% fewer preemptions, migrations, and 75% fewer scheduler invocations), and being comparable to those of suboptimal schedulers (within only 12% more preemptions/migrations). Additionally, the evaluation results show that NABLR completes more task instances when compared with ASEDZL, which yields a greater system output accuracy. Copyright

Improved real-time scheduling for periodic tasks on multiprocessors

Due to increasing numbers of real-time high-performance applications like control systems, autonomous robots, financial systems, scheduling these real-time applications on HPC resources has become an important problem. This paper presents a novel real-time multiprocessor scheduling algorithm, called Notional Approximation for Balancing Load Residues (NABLR), which heuristically selects tasks for execution by taking into account their residual loads and laxities. The NABLR schedule is created by considering a sequence of inter-arrival intervals (IAI) between two consecutive job arrivals of any task and using a heuristic to carefully plan task execution to fully utilize available resources in each of these intervals and avoid deadline misses as much as possible. Performance evaluation shows that NABLR outperforms previously known efficient algorithms (i.e. EDF and EDZL) in successfully scheduling sets of tasks in which total utilization of each task set equals available resource capacity, performing the closest to an optimal algorithm such as LLREF and Pfair. Out of 2500 randomly selected high-utilization task sets, NABLR can schedule up to 97.9% of the sets versus 63.2% by the best known efficient algorithm. In addition, the overheads of NABLR schedule are significantly smaller than those of optimal schedules (on average 80.57% fewer preemptions, migrations and 75.52% fewer scheduler invocations than those of LLREF) and comparably efficient to those of suboptimal schedules (fewer or nearly the same number of invocations as EDZL and ASEDZL, but within only 0.12% more preemptions/migrations than ASEDZL). NABLR has the same time complexity as other previously proposed efficient algorithms.

Towards closed-loop brain-machine experiments across wide-area networks

Experiments for the online closed-loop control of neural prosthetics require feedback within 100ms. In a typical neurophysiology laboratory with local computing machines, a majority of this time is spent on acquiring and analyzing the neural signals and a minority (i.e. less than a millisecond) is actual data transfer among machines on local- or campus-area networks. However, the local computing machines may not offer the computational resources necessary for running complex algorithms or scenarios that have been recently proposed. While scientists can take advantage of remote computing resource providers, wide-area networks present much larger latencies that can affect an online experiment. This work presents a split modeling approach that allows the execution of a controller on the neurophysiology resource and the execution of computationally intensive modeling and adaptation algorithms on a remote datacenter, even with the inevitable network latency. Simulation results are presented to quantify how the accuracy of the controller is affected by the split modeling approach in the presence of delays, and to demonstrate that scientists can take advantage of remotely available massive resources.