PARALLEL REAL-TIME OPTIMIZATION: BEYOND SPEEDUP

This paper describes two experiments carried out in order to investigate the role of visuals in multimodal answer presentations for a medical question answering system. First, a production experiment was carried out to determine which modalities people choose to answer different types of questions. In this experiment, participants had to create (multimodal) presentations of answers to general medical questions. The collected answer presentations were coded on the presence of visual media (i.e., photos, graphics, and animations) and their function. The results indicated that participants presented the information in a multimodal way. Moreover, significant differences were found in the presentation of different answer and question types. Next, an evaluation experiment was conducted to investigate how users evaluate different types of multimodal answer presentations. In this second experiment, participants had to assess the informativity and attractiveness of answer presentations for different types of medical questions. These answer presentations, originating from the production experiment, were manipulated in their answer length (brief vs. extended) and their type of picture (illustrative vs. informative). After the participants had assessed the answer presentations, they received a post- test in which they had to indicate how much they had recalled from the presented answer presentations. The results showed that answer presentations with an informative picture were evaluated as more informative and more attractive than answer presentations with an illustrative picture. The results for the post-test tentatively indicated that learning from answer presentations with an informative picture leads to a better learning performance than learning from purely textual answer presentations.

This research was part of a larger study into student performance in senior chemistry with regard to question type and content.This paper examines student perceptions about question type and context and compares these perceptions to actual performance.How students perceive different types of questions and how it influences their self-belief and motivation were the focus of this study.Student responses to different styles or types of questions have been well researched over time.In this study Year 11 chemistry students were quizzed about their preferences to Multiple-Choice questions and Open Response question types and how the presence of each type was likely to influence their test performance.Student's perceptions were then correlated to their actual performance on sample chemistry tests.Students generally preferred MCQ questions and believed they were likely to perform better on these questions regardless of the topic.Test results did not always support this confidence.Suggestions for further research are also made.

The present study aimed to explore the types of classroom questions which Jordanian English language teachers ask. The sample of the study consisted of 77 teachers who were randomly selected from different public and private schools in Amman- Jordan. A total of 1574 classroom questions were collected and analyzed using descriptive statistics, t test and analysis of variance. The results showed that 80% of teachers’ questions were on low thinking levels; 77% were closed-ended questions; and 86% were display questions. The results also indicated that teachers used higher thinking questions, more referential questions, and more open- ended questions at upper basic stage and secondary stage. It was recommended that EFL teachers in Jordan ask different types of questions at each grade level.

The DBSCAN method for spatial clustering has received significant attention due to its applicability in a variety of data analysis tasks. There are fast sequential algorithms for DBSCAN in Euclidean space that take $O(n\log n)$ work for two dimensions, sub-quadratic work for three or more dimensions, and can be computed approximately in linear work for any constant number of dimensions. However, existing parallel DBSCAN algorithms require quadratic work in the worst case, making them inefficient for large datasets. This paper bridges the gap between theory and practice of parallel DBSCAN by presenting new parallel algorithms for Euclidean exact DBSCAN and approximate DBSCAN that match the work bounds of their sequential counterparts, and are highly parallel (polylogarithmic depth). We present implementations of our algorithms along with optimizations that improve their practical performance. We perform a comprehensive experimental evaluation of our algorithms on a variety of datasets and parameter settings. Our experiments on a 36-core machine with hyper-threading show that we outperform existing parallel DBSCAN implementations by up to several orders of magnitude, and achieve speedups by up to 33x over the best sequential algorithms.

We present a parallel Delaunay refinement algorithm for generating well-shaped meshes in both two and three dimensions. Like its sequential counterparts, the parallel algorithm iteratively improves the quality of a mesh by inserting new points, the Steiner points, into the input domain while maintaining the Delaunay triangulation. The Steiner points are carefully chosen from a set of candidates that includes the circumcenters of poorly-shaped triangular elements. We introduce a notion of independence among possible Steiner points that can be inserted simultaneously during Delaunay refinements and show that such a set of independent points can be constructed efficiently and that the number of parallel iterations is O( log 2Δ), where Δ is the spread of the input — the ratio of the longest to the shortest pairwise distances among input features. In addition, we show that the parallel insertion of these set of points can be realized by sequential Delaunay refinement algorithms such as by Ruppert's algorithm in two dimensions and Shewchuk's algorithm in three dimensions. Therefore, our parallel Delaunay refinement algorithm provides the same shape quality and mesh-size guarantees as these sequential algorithms. For generating quasi-uniform meshes, such as those produced by Chew's algorithms, the number of parallel iterations is in fact O( log Δ). To the best of our knowledge, our algorithm is the first provably polylog(Δ) time parallel Delaunay-refinement algorithm that generates well-shaped meshes of size within a constant factor of the best possible.

Research evidence can play an important role in each stage of decision-making, evidence-support systems play a key role in aligning the demand for and supply of evidence. This paper provides guidance on what type of study designs most suitably address questions asked by decision-makers. This study used a two-round online Delphi approach, including methodological experts in different areas, disciplines, and geographic locations. Participants prioritized study designs for each of 40 different types of question, with a Kendall’s W greater than 0.6 and reaching statistical significance (p<0.05) considered as a consensus. For each type of question, we sorted the final rankings based on their median ranks and interquartile ranges, and listed the four study designs with the highest median ranks. Participants provided 29 answers in the two rounds of the Delphi, and reached a consensus for 28 (out of the 40) questions (eight in the first round and 20 in the second). Participants achieved a consensus for 8 of 15 questions in stage I (clarifying a societal problem, its causes, and potential impacts), 12 of 13 in stage II (finding options to address a problem) and four of six in each of stages III (implementing or scaling-up an option) and IV (monitoring implementation and evaluating impact). This paper provides guidance on what study designs are more suitable to give insights on 28 different types of questions. Decision-makers, evidence intermediaries (, researchers and funders can use this guidance to make better decisions on what type of study design to commission, use or fund when answering specific needs.

Over the years many interesting and efficient parallel algorithms have been developed to solve a wide variety of problems, but not much attention has been paid to studying the inherent parallelism in sequential algorithms---i.e., understanding the depth of their dependence structure, and how shallow dependence structures might beused to develop efficient parallel implementations. In this talk I will describe recent work on analyzing the dependence depth of iterative sequential algorithms---ones that loop over a collection of elements. Many of these algorithms have deep dependence chains in the worst case, but shallow chains (polylog w.h.p.) if the elements are randomly ordered. Examples include many fundamental algorithms: the Knuth shuffle for random permutations, sorting by insertion into a binary search tree, greedy maximal independent set (MIS), greedy maximal matching, greedy graph-coloring, counting cycles in a permutation, incremental k-dimensional linear programming, and incremental 2d Delaunay triangulation. An advantage of the approach is that it can lead to very simple and efficient parallel algorithms. Our MIS algorithm, for example can be coded in a dozen or so lines, and is significantly faster than Luby's algorithm on modern multicore machines. Also the approach encourages snapping the view that sequential and parallel algorithms are distinct, and instead thinking of algorithms, in general, as collections of instructions with dependences among them.

This study aims to develop an instrument for HOTS questions with the help of the Wondershare Quiz Creator (WQC) application on Momentum and Impulse materials with design and material feasibility, suitable settings for HOTS questions with four types of HOTS questions, namely Multiple Choice, Multiple Responses, Sequence and Matching. The research method used is Research and Development (R &amp; D). This type of research is used to adapt the research design by Borg &amp; Gall. The product development stages consist of research and data collection, planning, product development, product validation, product revision, and product results. The data collection technique used expert validation in developing HOTS questions based on CBT, then the data were analyzed quantitatively and descriptively. The analysis shows that the validity of the design has an average value of 4.21 with very high quality or validity and the validity of the material has an average value of 3.75 with high quality or valid. The highest scores for design and material validity were multiple responses 4.22 and 3.79. At the levels on C4, C5, and C6, there is no difference in the validity and complexity of thinking caused by different types of questions. Keywords: CBT, HOTS, Momentum and Impulse, Wondershare quiz creator

Graph edit distance (GED) is a measure for quantifying the similarity between two graphs. Because of its flexibility and versatility, GED is widely used in many real applications. However, the main disadvantage of GED is its high computational cost. Many solutions have been proposed to speed up GED computation, but most of them focus on developing serial algorithms and only very few solutions consider parallel computing. In this paper, we study a parallel GED computation to elaborate a fast and precise algorithm. Unlike existing solutions that utilize either a depth-first or a best-first search, we propose a hybrid approach that combines depth-first and best-first search paradigms. Our approach can quickly find tighter GED upper bounds, and effectively prune the search space using the upper bounds. Based on the approach, we develop an efficient parallel GED computation algorithm named ${\sf HGED}$ . To maximize thread utility, ${\sf HGED}$ is also equipped with a novel dynamic load balancing scheme whose main focus is on reducing the overhead of thread synchronization. Experimental results on widely used real datasets show that, on average, ${\sf HGED}$ outperforms the state-of-the art serial algorithm ${\sf AStar}^{+}$ - ${\sf LSa}$ by 6 times and the state-of-the parallel algorithm ${\sf PGED}$ by 4 times.

Data partitioning algorithms aiming to minimize the execution time and the energy of computations in self-adaptable data-parallel applications on modern extreme-scale multicore platforms must address two critical challenges. First, they must take into account the new complexities inherent in these platforms such as severe resource contention and non-uniform memory access. Second, they must have low practical runtime and memory costs. The sequential data partitioning algorithms addressing the first challenge have a theoretical time complexity of O( $m * m * p * p$ ) where $m$ is the number of points in the discrete speed/energy function and $p$ is the number of available processors. They, however, exhibit high practical runtime cost and excessive memory footprint, therefore, rendering them impracticable for employment in self-adaptable applications executing on extreme-scale multicore platforms. We present, in this paper, the parallel data partitioning algorithms that address both the challenges. They take as input the functional models of performance and energy consumption against problem size and output workload distributions, which are globally optimal solutions. They have a low time complexity of O( $m * m * p$ ) thereby providing a linear speedup of O( $p$ ) and low memory complexity of O( $n$ ) where $n$ is the workload size expressed as a multiple of granularity. They employ dynamic programming approach, which also facilitates the easier integration of performance and energy models of communications. We experimentally study the practical cost of application of our algorithms in two data-parallel applications, matrix multiplication and fast Fourier transform, on a cluster in Grid’5000 platform. We demonstrate that their practical runtime and memory costs are low making them ideal for employment in self-adaptable applications. We also show that the parallel algorithms exhibit tremendous speedups over the sequential algorithms. Finally, using theoretical analysis for a forecast exascale platform, we demonstrate that the parallel algorithms have negligible execution times compared to the matrix multiplication application executing on the platform.

The computational complexity of internal diffusion-limited aggregation (DLA) is examined from both a theoretical and a practical point of view. We show that for two or more dimensions, the problem of predicting the cluster from a given set of paths is complete for the complexity class CC, the subset of P characterized by circuits composed of comparator gates. CC-completeness is believed to imply that, in the worst case, growing a cluster of size n requires polynomial time in n even on a parallel computer. A parallel relaxation algorithm is presented that uses the fact that clusters are nearly spherical to guess the cluster from a given set of paths, and then corrects defects in the guessed cluster through a nonlocal annihilation process. The parallel running time of the relaxation algorithm for two-dimensional internal DLA is studied by simulating it on a serial computer. The numerical results are compatible with a running time that is either polylogarithmic in n or a small power of n. Thus the computational resources needed to grow large clusters are significantly less on average than the worst-case analysis would suggest. For a parallel machine with k processors, we show that random clusters in d dimensions can be generated in $$\mathcal{O}$$ ((n/k+logk)n 2/d ) steps. This is a significant speedup over explicit sequential simulation, which takes $$\mathcal{O}$$ (n 1+2/d ) time on average. Finally, we show that in one dimension internal DLA can be predicted in $$\mathcal{O}$$ (logn) parallel time, and so is in the complexity class NC.

The mathematical Е-operating method is intended for transformation of the of differential equations system to the tracking electric drive mathematical model equations system. In contrast to the known algorithms for numerical integration, for example, in the Matlab-Simulink, E-method allows to synthesize of the transfer function of tracking electric drives for both sequential and parallel differential algorithms for working in real time on the basis of both software and hardware shifting registers. It is important to note that these algorithms cannot be implemented using Matlab-Simulink. Parallel algorithm provides greater performance than serial algorithm. Parallel algorithm can be implemented "conveyor" method of using multiple coprocessors at the same time. Method is an alternative of the means available in Matlab-Simulink programme for description and analysis of the tracking electric drive model. In the first part of the article the synthesis algorithm using traditional means of differential calculus and Laplace transforms describes. In the second part of the article a solution of the same problem with the use of the Е-operating method presents. The results obtained can be used in mechatronics, robotics, automatic control theory, in the practice of building looking for tracking electric drive.

Electronic circuits: by E. J. Angelo, Jr. 450 pages, diagrams, 6 × 9 in. New York, McGraw-Hill Book Co. Inc., 1958.Price, $9.00.

Three diagnostic rapid test kits (Chembio HIV-1/2 Stat-Pak, Alere DetermineTM HIV-1/2, and Core HIV-1/2) for human immunodeficiency virus types 1 and 2 (HIV-1/2) antibodies detection were evaluated against a gold standard fourth generation ELISA (Dia-Pro). Hundred and seventy two serum samples were collected from Lulubriggs Health Center, University of Port Harcourt, Rivers State. All samples were tested for HIV-1/2 using the three rapid test (parallel algorithm and serial algorithm), and retested using the 4th generation ELISA. The results obtained were compared with those from the ELISA. The DetermineTM rapid strips had sensitivity of 66.7%, specificity of 100%, positive predictive value 100%, negative predictive value 89.4% and total agreement of 91.3%. Stat-pak and Core HIV-1/2 rapid strips both had sensitivity of 71.7%, specificity of 100%, positive predictive value 100%, and negative predictive value 90.7% and total agreement of 92.4%. Determine was mostly used by the participant laboratories 18 of 30 (60%). The performance evaluation of the testing algorithm showed that parallel algorithm is more accurate in comparison to serial algorithm. The result of this study reveals that most rapid test are less sensitive and the accuracy of serial testing algorithm is low, this implies that most acute HIV infection will be missed with rapid assay and false negative results will be reported as actual negative with serial algorithm.

High-resolution adaptive-optical systems with thousands to millions of pixels will most likely have to employ serial- or matrix-addressed spatial light modulators (e.g., microelectromechanical-system-on-VLSI spatial light modulators). We compare parallel gradient descent adaptive-optics algorithms with serial gradient descent algorithms running on serially addressed modulators. While serial algorithms have previously been shown to require more iterations than parallel algorithms, we show that, because of the limitations of the databus, each serial iteration of the algorithm on a serial modulator requires significantly less time to complete than a parallel iteration, thereby favoring the serial algorithm when time to convergence is used as the performance metric. Thus, such high-resolution serially addressed devices are generally better matched to the serial-update wavefront correction algorithm owing to the data load penalty imposed by the bandwidth-limited databus of these modulators.