Performance and energy task migration model for heterogeneous clusters

The Journal of Supercomputing - This article presents a set of linear regression models to predict the impact of task migration on different objectives, like performance and energy consumption. It...     

A system-on-chip development of a neuro-fuzzy embedded agent for ambient-intelligence environments

This paper presents the development of a neuro-fuzzy agent for ambient-intelligence environments. The agent has been implemented as a system-on-chip (SoC) on a reconfigurable device, i.e., a field-programmable gate array. It is a hardware/software (HW/SW) architecture developed around a MicroBlaze processor (SW partition) and a set of parallel intellectual property cores for neuro-fuzzy modeling (HW partition). The SoC is an autonomous electronic device able to perform real-time control of the environment in a personalized and adaptive way, anticipating the desires and needs of its inhabitants. The scheme used to model the intelligent agent is a particular class of an adaptive neuro-fuzzy inference system with piecewise multilinear behavior. The main characteristics of our model are computational efficiency, scalability, and universal approximation capability. Several online experiments have been performed with data obtained in a real ubiquitous computing environment test bed. Results obtained show that the SoC is able to provide high-performance control and adaptation in a life-long mode while retaining the modeling capabilities of similar agent-based approaches implemented on larger computing machines.     

Symbiosis of nurse and machine through fuzzy logic: improved specificity of a neonatal pulse oximeter alarm

This article describes the theoretical underpinnings that preceded the design of a new neonatal pulse oximeter alarm that differentiates true from false alarms based on an artificial intelligence theory called "fuzzy logic." The connection between the intuition and sense of advocacy gained through neonatal primary nursing and the application of fuzzy logic to solve the problem of false alarms--that is, the symbiosis between nurse and machine--are explained. Emphasis is placed throughout on the importance of involving nurses in the development of the technology for which they are responsible.     

Filtering directory lookups in CMPs

Coherence protocols consume an important fraction of power to determine which coherence action to perform. Specifically, on CMPs with shared cache and directory-based coherence protocol implemented as a duplicate of local caches tags, we have observed that a big fraction of directory lookups cause a miss, because the block looked up is not allocated in any local cache. To reduce the number of directory lookups and therefore the power consumption, we propose to add a filter before the directory access.We introduce two filter implementations. In the first one, filtering information is explicitly kept in the shared cache for every block. In the second one, filtering information is decoupled from the shared cache organization, so the filter size does not depend on the shared cache size.We evaluate our filters in a CMP with 8 in-order processors with 4 threads each and a memory hierarchy with write-through local caches and a shared cache. We show that, for SPLASH2 benchmarks, the proposed filters reduce the number of directory lookups performed by 60% while power consumption is reduced by ∼28%. For Specweb2005, the number of directory lookups performed is reduced by 68% (44%), while directory power consumption is reduced by 19% (9%) using the first (second) filter implementation.     

Efficient Hardware/Software Implementation of an Adaptive Neuro-Fuzzy System

This paper describes the development of efficient hardware/software (HW/SW) neuro-fuzzy systems. The model used in this work consists of an adaptive neuro-fuzzy inference system modified for efficient HW/SW implementation. The design of two different on-chip approaches are presented: a high-performance parallel architecture for offline training and a pipelined architecture suitable for online parameter adaptation. Details of important aspects concerning the design of HW/SW solutions are given. The proposed architectures have been implemented using a system-on-a-programmable-chip. The device contains an embedded-processor core and a large field programmable gate array (FPGA). The processor provides flexibility and high precision to implement the learning algorithms, while the FPGA allows the development of high-speed inference architectures for real-time embedded applications.     

Shot boundary detection using Zernike moments in multi-GPU multi-CPU architectures

This paper presents an analysis of a Multi-GPU Multi-CPU environment, along with the different possible hybrid combinations. The analysis has been performed for a shot boundary detection application, based on Zernike moments, although it is general enough to be applied to many different application areas. A deep study of the performance, bottlenecks and design challenges is carried out showing the validity of this approach and achieving very high frame per second rates. In this paper, Zernike calculations are carried out on GPUs, taking advantage of a packing strategy proposed to minimize host-device communication time.     

Anaerobic digestion of gelatinous water at laboratory and pilot scale and nitrogen inhibition.

The anaerobic digestion of the liquid residue (gelatinous water) coming from the production of fat from animal residue, was studied at laboratory and pilot scale. Biodegradability (>98%) and biogas potential (675 mL of biogas/g of COD(applied)) of this wastewater are very high. However, due to the high content on nitrogen, an inhibition of the anaerobic activity was observed for quite low concentrations of N-NH(3). Dilution of the wastewater and pH regulation in the reactor around 7.3 are the 2 solutions which were investigated to overcome the nitrogen inhibition at industrial scale. These two solutions were validated at laboratory scale in an anaerobic SBR and then onsite at pilot scale in a continuous reactor. A stable anaerobic digestion was observed in both reactors showing that no nitrogen inhibition was obtained when N-NH(3) concentration in the reactor was kept low.     

Thermoelectric properties in Ca3Co4−xMnxOy ceramics

Ca₃Co_4?xMn_xO_y polycrystalline thermoelectric ceramics with small amounts of Mn have been prepared by the classical solid state method. X-ray diffraction data have shown that Ca₃Co₄O₉ is the major phase, with small amounts of the Ca₃Co₂O₆ one. Moreover, they show that the Mn has been incorporated into these two phases. Electrical resistivity decreases, compared with the values for undoped samples, with Mn content until a minimum for the 0·03 doped ones, increasing for higher Mn substitution. Seebeck coefficient does not change in all the measured temperature range, independently of Mn content. The improvement in electrical resistivity leads ～30% higher power factor values for the 0·03 Mn doped samples than that obtained in the undoped ones. The maximum power factor at 800°C, ～0·28 mW K^?2 m^?1, is close to that obtained in much higher density samples, clearly indicating the good thermoelectric properties of these samples.     

Effect of Temperature on C3S and C3S + Nanosilica Hydration and C–S–H Structure

This study aimed to monitor the effect of temperature and the addition of nanosilica on the nanostructure of the C–S–H gel forming during tricalcium silicate (C₃S) hydration. Two types of paste were prepared from a synthesized T₁ C₃S. The first consisted of a blend of deionized water and C₃S at a water/solid ratio of 0.425. In the second, a 90 wt% C₃S + 10 wt% of nanosilica blend was mixed with water at a water/solid ratio of 0.7. The pastes were stored in closed containers at 100% RH and 25°C, 40°C, or 65°C. The hydration reaction was detained after 1, 14, 28, or 62 d with acetone, and then pastes were studied by ²⁹Si magic angle spinning nuclear magnetic resonance (²⁹Si MAS NMR).The main conclusion was that adding nSA expedites C₃S hydration at any age or temperature and modifies the structure of the C–S–H gel formed, two types of C–S–H gel appear. At 25°C and 40°C, more orderly, longer chain gels are initially (1 d) obtained as a result of the pozzolanic reaction between nSA and portlandite (CH) (C–S–H_II gel formation). Subsequently, ongoing C₃S hydration and the concomitant flow of dimers shorten the mean chain length in the gel.     

PLGA nanodepots co-encapsulating prostratin and anti-CD25 enhance primary natural killer cell antiviral and antitumor function

Nano Research - Natural killer (NK) cells are attractive effector cells of the innate immune system against human immunodeficiency virus (HIV) and cancer. However, NK cell therapies are limited by...