Adaptive web sites may offer automated recommendations generated through any number of well-studied techniques including collaborative, content-based and knowledge-based recommendation. Each of these techniques has its own strengths and weaknesses. In search of better performance, researchers have combined recommendation techniques to build hybrid recommender systems. This chapter surveys the space of two-part hybrid recommender systems, comparing four different recommendation techniques and seven different hybridization strategies. Implementations of 41 hybrids including some novel combinations are examined and compared. The study finds that cascade and augmented hybrids work well, especially when combining two components of differing strengths.

/pdf/hybrid-web-recommender-systems-5c2ch4kz7c.pdf

Hybrid web recommender systems

When building a unified vision system or gradually adding new capabilities to a system, the usual assumption is that training data for all tasks is always available. However, as the number of tasks grows, storing and retraining on such data becomes infeasible. A new problem arises where we add new capabilities to a Convolutional Neural Network (CNN), but the training data for its existing capabilities are unavailable. We propose our Learning without Forgetting method, which uses only new task data to train the network while preserving the original capabilities. Our method performs favorably compared to commonly used feature extraction and fine-tuning adaption techniques and performs similarly to multitask learning that uses original task data we assume unavailable. A more surprising observation is that Learning without Forgetting may be able to replace fine-tuning with similar old and new task datasets for improved new task performance.

Learning without Forgetting

Semisolid metal (SSM) processingis a relatively new technology for metal forming. Different from the conventional metal forming technologies which use either solid metals (solid state processing) or liquid metals (casting) as starting materials, SSM processing deals with semisolid slurries, in which non-dendritic solid particles are dispersed in a liquid matrix. Semisolid metal slurries exhibit distinctive rheological characteristics: the steady state behaviour is pseudoplastic (or shear thinning), while the transient state behaviour is thixotropic. All the currently available technologies for SSM processing have been developed based on those unique rheological properties, which in turn originate from their non-dendritic microstructures. Year 2001 marks the 30th anniversary of the concept of SSM processing. Today, SSM processing has established itself as a scientifically sound and commercially viable technology for production of metallic components with high integrity, improved mechanical properti...

Semisolid metal processing

Noel Cressie and Christopher WikleHardcover: 624 pagesYear: 2011Publisher: John WileyISBN-13: 978-0471692744Here is the new reference book about spatial and spatio-temporal statistical modeling! No...

Statistics for Spatio-Temporal Data

Cyberphysical systems (CPSs) are new class of engineered systems that offer close interaction between cyber and physical components. The field of CPS has been identified as a key area of research, and CPSs are expected to play a major role in the design and development of future systems. In this paper, we survey recent advancements made in the development and applications of CPSs. We classify the existing research work based on their characteristics and identify the future challenges. We also discuss the examples of prototypes of CPSs. The aim of this survey is to enable researchers and system designers to get insights into the working and applications of CPSs and motivate them to propose novel solutions for making wide-scale adoption of CPS a tangible reality.

Design Techniques and Applications of Cyberphysical Systems: A Survey

Most of the existing research on multiprocessor mixed-criticality scheduling has focused on ensuring schedulability of the task set when the criticality level of the system increases. Furthermore, upon increasing the criticality level, most of these scheduling approaches suspend the execution of the lower criticality tasks in order to guarantee the schedulability of the higher criticality tasks. Although there exists a couple of approaches to facilitate the execution of some of the lower criticality tasks using the available slack in the system, to the best of our knowledge, there is no efficient mechanism that allows for eventually decreasing the criticality level of the system in order to resume the execution of the suspended lower criticality tasks. We refer to the problem of deciding when and how to lower the criticality level of the system as the "Safe Criticality Reduction" (SCR) problem. In this work, we design two solutions that are independent of the number of criticality levels and the number of processors and prove their correctness. The first protocol can be applied to any fixed task priority scheduler, and an upper-bound on the suspension delay suffered by the lower criticality tasks is presented. The second protocol can be applied to any fixed job priority scheduler and hence dominates the first protocol albeit with a higher run-time overhead. To the best of our knowledge, these are the first solutions for the SCR problem on multiprocessor platforms.

/pdf/two-protocols-to-reduce-the-criticality-level-of-5d65i7epx2.pdf

Two protocols to reduce the criticality level of multiprocessor mixed-criticality systems

Mixed-Criticality systems are arising due to the push from several major industries including avionics and automotive, where functionalities with different safety criticality levels are integrated into a modern computing platform to reduce size, weight and energy. The state-of-the-art research has focused on protecting critical tasks under the threat of task overrun, which is achieved by terminating less critical tasks or degrading their services to free system resources to guarantee critical tasks. We take in this paper a different approach to protecting critical tasks by embracing rich features of modern computing platforms. In particular, we explore dynamic processor speedup to aid the scheduling of mixed-criticality systems. We show that speedup in situation of overrun can not only help to protect the timeliness of critical tasks, but also to improve the degraded services for less critical tasks. Furthermore, we show that speedup is even more attractive as it can help the system to recover faster to normal operation. Thus, speedup could only be temporarily required and incur low cost. The proposed techniques are validated by both theoretical analysis and experimental results with an industrial flight management system and extensive simulations.

Run and be safe: mixed-criticality scheduling with temporary processor speedup

In this work we present the first formal study on optimizing the energy utilization of energy harvesting embedded systems while giving bounds on the minimum energy usage. Furthermore, to deal with the uncertainty inherent to solar energy harvesting we propose to use (i) a finite horizon scheme, and (ii) anon-uniformly scaled energy estimation based on an astronomical model. Under certain realistic assumptions, the finite horizon scheme can provide guarantees on minimum energy utilization, and therefore minimum utility. We show that a single non-uniform scaling function is applicable to solar energy traces from diverse locations. We further propose and evaluate a piece-wise linear approximation for efficient implementation as a small look-up table for resource constrained embedded systems. With extensive experimental evaluation for eight publicly available datasets and two datasets collected with our own deployments, we quantitatively establish that the proposed solution is highly effective at providing a guaranteed minimum utilization, and significantly out-performs four previously proposed solutions.

/pdf/optimal-power-management-with-guaranteed-minimum-energy-18b1hf6ymg.pdf

Optimal Power Management with Guaranteed Minimum Energy Utilization for Solar Energy Harvesting Systems

With increasing power densities, runtime thermal management is becoming a necessity in today's systems, especially so for highly integrated Multi-Processor Systems-on-Chip (MPSoCs). In this paper, we propose a neural network (NN) based approach to implement an on-chip thermal simulator to aid such runtime management for MPSoCs. The proposed method combines the advantage of approximating the thermal properties of the chip as a linear system with the ease of fully parallel analog implementation of NNs. We perform a case study with the Niagara UltraSPARC Tl MPSoC for real-life applications, benchmarking our results with an accurate higher order Runge-Kutta (RK4) solver, that is employed in tools such as HotSpot. Within a few gate delays, the proposed NN design can simulate temperatures of the MPSoC 500 ms into the future — corresponding to thousands of iterations of the RK4 solver, with a maximum error of 1–2 K.

Neural network based on-chip thermal simulator

A blockchain configuration may be used to store a distributed ledger for an energy optimization procedure. One example method of operation may include measuring energy metrics associated with network devices operating on a network via meter devices, identifying potential changes to existing energy usage of the network based on the energy metrics, logging the energy metrics and the potential changes as part of a distributed ledger, and storing the distributed ledger in a blockchain block.

Pratyush Kumar

Papers

Two protocols to reduce the criticality level of multiprocessor mixed-criticality systems

Run and be safe: mixed-criticality scheduling with temporary processor speedup

Optimal Power Management with Guaranteed Minimum Energy Utilization for Solar Energy Harvesting Systems

Neural network based on-chip thermal simulator

Autonomous peer-to-peer energy networks operating on a blockchain