Disk

2020 ◽  
Vol 14 (3) ◽  
pp. 351-363
Author(s):  
Yue Wang ◽  
Ruiqi Xu ◽  
Zonghao Feng ◽  
Yulin Che ◽  
Lei Chen ◽  
...  
Keyword(s):  
Shared Memory ◽  
Experimental Studies ◽  
Similarity Measures ◽  
Optimization Techniques ◽  
Personalized Recommendation ◽  
Single Source ◽  
Distributed Environment ◽  
Parallel Scalability ◽  
Distributed Framework ◽  
Online Queries

Measuring similarities among different nodes is important in graph analysis. SimRank is one of the most popular similarity measures. Given a graph G ( V , E ) and a source node u , a single-source Sim-Rank query returns the similarities between u and each node v ∈ V. This type of query is often used in link prediction, personalized recommendation and spam detection. While dealing with a large graph is beyond the ability of a single machine due to its limited memory and computational power, it is necessary to process single-source SimRank queries in a distributed environment, where the graph is partitioned and distributed across multiple machines. However, most current solutions are based on shared-memory model, where the whole graph is loaded into a shared memory and all processors can access the graph randomly. It is difficult to deploy such algorithms on shared-nothing model. In this paper, we present DISK, a distributed framework for processing single-source SimRank queries. DISK follows the linearized formulation of SimRank, and consists of offline and online phases. In the offline phase, a tree-based method is used to estimate the diagonal correction matrix of SimRank accurately, and in the online phase, single-source similarities are computed iteratively. Under this framework, we propose different optimization techniques to boost the indexing and queries. DISK guarantees both accuracy and parallel scalability, which distinguishes itself from existing solutions. Its accuracy, efficiency, parallel scalability and scalability are also verified by extensive experimental studies. The experiments show that DISK scales up to graphs of billions of nodes and edges, and answers online queries within seconds, while ensuring the accuracy bounds.

Combining Response Surface Method and Metaheuristic Algorithms for Optimizing SPIF Process

2021 ◽  
Vol 11 (4) ◽  
pp. 1-25
Author(s):  
Amr Ahmed Shaaban ◽  
Omar Mahmoud Shehata
Keyword(s):  
Response Surface ◽  
Response Surface Method ◽  
Single Point ◽  
Experimental Studies ◽  
Optimization Techniques ◽  
Parameters Optimization ◽  
Second Phase ◽  
Fe Model ◽  
Optimum Conditions ◽  
Surface Method

Recently, studies have focused on optimization as a method to reach the finest conditions for metal forming processes. This study tests various optimization techniques to determine the optimum conditions for single point incremental forming (SPIF). SPIF is a die-less forming process that depends on moving a tool along a path designed for a specific feature. As it involves various parameters, optimization based on experimental studies would be costly, hence a finite element model (FE-model) for the SPIF process is developed and validated through experimental results. In the second phase, statistical analyses based on the response surface method (RSM) are conducted. The optimum conditions are determined using the desirability optimization method, in addition to two metaheuristic optimization algorithms, namely genetic algorithm (GA) and particle swarm optimization (PSO). The results of all optimization techniques are compared to each other and a confirmation test using the FE-model is subsequently performed.

Performance portable parallel programming of heterogeneous stencils across shared-memory platforms with modern Intel processors

2019 ◽  
Vol 33 (3) ◽  
pp. 534-553 ◽  
Author(s):  
Lukasz Szustak ◽  
Pawel Bratek
Keyword(s):  
Shared Memory ◽  
Memory Systems ◽  
Optimization Techniques ◽  
Utilization Rate ◽  
Problem Size ◽  
Geophysical Model ◽  
Step Procedure ◽  
Wide Range ◽  
Sustained Performance ◽  
Portable Parallel Programming

In this work, we take up the challenge of performance portable programming of heterogeneous stencil computations across a wide range of modern shared-memory systems. An important example of such computations is the Multidimensional Positive Definite Advection Transport Algorithm (MPDATA), the second major part of the dynamic core of the EULAG geophysical model. For this aim, we develop a set of parametric optimization techniques and four-step procedure for customization of the MPDATA code. Among these techniques are: islands-of-cores strategy, (3+1)D decomposition, exploiting data parallelism and simultaneous multithreading, data flow synchronization, and vectorization. The proposed adaptation methodology helps us to develop the automatic transformation of the MPDATA code to achieve high sustained scalable performance for all tested ccNUMA platforms with Intel processors of last generations. This means that for a given platform, the sustained performance of the new code is kept at a similar level, independently of the problem size. The highest performance utilization rate of about 41–46% of the theoretical peak, measured for all benchmarks, is provided for any of the two-socket servers based on Skylake-SP (SKL-SP), Broadwell, and Haswell CPU architectures. At the same time, the four-socket server with SKL-SP processors achieves the highest sustained performance of around 1.0–1.1 Tflop/s that corresponds to about 33% of the peak.

An Artificial Bee Colony-Guided Approach for Electro-Encephalography Signal Decomposition-Based Big Data Optimization

2020 ◽  
Vol 19 (02) ◽  
pp. 561-600
Author(s):  
Selcuk Aslan
Keyword(s):  
Big Data ◽  
Artificial Bee Colony ◽  
Optimization Problems ◽  
Experimental Studies ◽  
Pso Algorithm ◽  
Optimization Techniques ◽  
Abc Algorithm ◽  
Bee Colony ◽  
De Algorithm ◽  
Data Optimization

The digital age has added a new term to the literature of information and computer sciences called as the big data in recent years. Because of the individual properties of the newly introduced term, the definitions of the data-intensive problems including optimization problems have been substantially changed and investigations about the solving capabilities of the existing techniques and then developing their specialized variants for big data optimizations have become important research topic. Artificial Bee Colony (ABC) algorithm inspired by the clever foraging characteristics of the real honey bees is one of the most successful swarm intelligence-based metaheuristics. In this study, a new ABC algorithm-based technique that is named source-linked ABC (slinkABC) was proposed by considering the properties of the optimization problems related with the big data. The slinkABC algorithm was tested on the big data optimization problems presented at the Congress on Evolutionary Computation (CEC) 2015 Big Data Optimization Competition. The results obtained from the experimental studies were compared with the different variants of the ABC algorithm including gbest-guided ABC (GABC), ABC/best/1, ABC/best/2, crossover ABC (CABC), converge-onlookers ABC (COABC), quick ABC (qABC) and modified gbest-guided ABC (MGABC) algorithms. In addition to these, the results of the proposed ABC algorithm were also compared with the results of the Differential Evolution (DE) algorithm, Genetic algorithm (GA), Firefly algorithm (FA), Phase-Based Optimization (PBO) algorithm and Particle Swarm Optimization (PSO) algorithm-based approaches. From the experimental studies, it was understood that the ABC algorithm modified by considering the unique properties of the big data optimization problems as in the slinkABC produces better solutions for most of the tested instances compared to the mentioned optimization techniques.

scholarly journals Hybrid Measuring the Similarity Value Based on Genetic Algorithm for Improving Prediction in A Collaborative Filtering Recommendation System.

2021 ◽  
Vol 10 (2) ◽  
Author(s):  
Muaadh Abdo Mohammed Ahmed AL sabri
Keyword(s):  
Collaborative Filtering ◽  
Recommendation System ◽  
Forecast Accuracy ◽  
Similarity Measures ◽  
Nearest Neighbors ◽  
Personalized Recommendation ◽  
Education Economics ◽  
Standard Methods ◽  
Wide Range ◽  
Suitable Product

In recent years, the Recommendation System (RS) has a wide range of applications in several fields, like Education, Economics, Scientific Researches and other related fields. The Personalized Recommendation is effective in increasing RS's accuracy, based on the user interface, preferences and constraints seek to predict the most suitable product or services. Collaborative Filtering (CF) is one of the primary applications that researchers use for the prediction of the accuracy rating and recommendation of objects. Various experts in the field are using methods like Nearest Neighbors (NN) based on the measures of similarity.  However, similarity measures use only the co-rated item ratings while calculating the similarity between a pair of users or items. The two standard methods used to measure similarities are Cosine Similarity (CS) and Person Correlation Similarity (PCS). However, both are having drawbacks, and the present piece of the investigation will approach through the optimized Genetic Algorithms (GA) to improve the forecast accuracy of RS using the merge output of CS with PCS based on GA methods. The results show GA's superiority and its ability to achieve more correct predictions than CS and PCS.

scholarly journals Recommendation Framework Combining User Interests with Fashion Trends in Apparel Online Shopping

2019 ◽  
Vol 9 (13) ◽  
pp. 2634 ◽  
Author(s):  
Ok ◽  
Lee ◽  
Kim
Keyword(s):  
Random Walk ◽  
Collaborative Filtering ◽  
Real World ◽  
Large Scale ◽  
Online Shopping ◽  
Experimental Studies ◽  
Empirical Evaluation ◽  
Personalized Recommendation ◽  
User Interests ◽  
Sparsity Problem

Although fashion-related products account for most of the online shopping categories, it becomes more difficult for users to search and find products matching their taste and needs as the number of items available online increases explosively. Personalized recommendation of items is the best method for both reducing user effort on searching for items and expanding sales opportunity for sellers. Unfortunately, experimental studies and research on fashion item recommendation for online shopping users are lacking. In this paper, we propose a novel recommendation framework suitable for online apparel items. To overcome the rating sparsity problem of online apparel datasets, we derive implicit ratings from user log data and generate predicted ratings for item clusters by user-based collaborative filtering. The ratings are combined with a network constructed by an item click trend, which serves as a personalized recommendation through a random walk. An empirical evaluation on a large-scale real-world dataset obtained from an apparel retailer demonstrates the effectiveness of our method.

scholarly journals Strength Design of Compressed Reinforced Concrete Elements by Deformation Method Based on Extreme Criterion

2018 ◽  
Vol 7 (3.2) ◽  
pp. 334 ◽  
Author(s):  
Oleksandr Shkurupiy ◽  
Dmytro Lazariev ◽  
Yurii Davydenko
Keyword(s):  
Reinforced Concrete ◽  
Numerical Optimization ◽  
Experimental Studies ◽  
Optimization Techniques ◽  
Deformation Method ◽  
Strength Design ◽  
Concrete Elements

Investigations of the normal sections strength of compressed elements using a deformation method were performed. The shape of the section, the class of concrete and the percentage of reinforcement were taken into account when performing analytical calculations. Analytical, numerical, optimization techniques etc. were used for solving of this task. The results of the analytical calculations and the data of the experimental studies were compared.  

Sign in / Sign up

Export Citation Format

Share Document