scholarly journals Improving WalkSAT for Random 3-SAT Problems

2020 ◽  
Vol 26 (2) ◽  
pp. 220-243
Author(s):  
Huimin Fu ◽  
Yang Xu ◽  
Shuwei Chen ◽  
Jun Liu
Keyword(s):  
Phase Transition ◽  
Ant Colony Algorithm ◽  
State Of The Art ◽  
Stochastic Local Search ◽  
Improved Genetic Algorithm ◽  
Initial Assignment ◽  
Sat Solver ◽  
Random Instances ◽  
Improved Ant Colony Algorithm ◽  
Better Than

Stochastic local search (SLS) algorithms are well known for their ability to efficiently find models of random instances of the Boolean satisfiability (SAT) problems. One of the most famous SLS algorithms for SAT is called WalkSAT, which has wide influence and performs well on most of random 3-SAT instances. However, the performance of WalkSAT lags far behind on random 3-SAT instances equal to or greater than the phase transition ratio. Motivated by this limitation, in the present work, firstly an allocation strategy is introduced and utilized in WalkSAT to determine the initial assignment, leading to a new algorithm called WalkSATvav. The experimental results show that WalkSATvav significantly outperforms the state-of-the-art SLS solvers on random 3-SAT instances at the phase transition for SAT Competition 2017. However, WalkSATvav cannot rival its competitors on random 3-SAT instances greater than the phase transition ratio. Accordingly, WalkSATvav is further improved for such instances by utilizing a combination of an improved genetic algorithm and an improved ant colony algorithm, which complement each other in guiding the search direction. The resulting algorithm, called WalkSATga, is far better than WalkSAT and significantly outperforms some previous known SLS solvers on random 3-SAT instances greater than the phase transition ratio from SAT Competition 2017. Finally, a new SAT solver called WalkSATlg, which combines WalkSATvav and WalkSATga, is proposed, which is competitive with the winner of random satisfiable category of SAT competition 2017 on random 3-SAT problem.

scholarly journals Scoring Functions Based on Second Level Score for k-SAT with Long Clauses

2014 ◽  
Vol 51 ◽  
pp. 413-441 ◽  
Author(s):  
S. Cai ◽  
C. Luo ◽  
K. Su
Keyword(s):  
Phase Transition ◽  
Computational Complexity ◽  
Local Search ◽  
State Of The Art ◽  
Scoring Function ◽  
Experimental Results ◽  
Great Success ◽  
Stochastic Local Search ◽  
Scoring Functions ◽  
New Scoring

It is widely acknowledged that stochastic local search (SLS) algorithms can efficiently find models for satisfiable instances of the satisfiability (SAT) problem, especially for random k-SAT instances. However, compared to random 3-SAT instances where SLS algorithms have shown great success, random k-SAT instances with long clauses remain very difficult. Recently, the notion of second level score, denoted as "score_2", was proposed for improving SLS algorithms on long-clause SAT instances, and was first used in the powerful CCASat solver as a tie breaker. In this paper, we propose three new scoring functions based on score_2. Despite their simplicity, these functions are very effective for solving random k-SAT with long clauses. The first function combines score and score_2, and the second one additionally integrates the diversification property "age". These two functions are used in developing a new SLS algorithm called CScoreSAT. Experimental results on large random 5-SAT and 7-SAT instances near phase transition show that CScoreSAT significantly outperforms previous SLS solvers. However, CScoreSAT cannot rival its competitors on random k-SAT instances at phase transition. We improve CScoreSAT for such instances by another scoring function which combines score_2 with age. The resulting algorithm HScoreSAT exhibits state-of-the-art performance on random k-SAT (k>3) instances at phase transition. We also study the computation of score_2, including its implementation and computational complexity.

A new approach based on graph matching and evolutionary approach for sport scheduling problem

2020 ◽  
pp. 1-16
Author(s):  
Meriem Khelifa ◽  
Dalila Boughaci ◽  
Esma Aïmeur
Keyword(s):  
Graph Matching ◽  
State Of The Art ◽  
Travel Cost ◽  
Round Robin ◽  
New Approach ◽  
Traveling Tournament Problem ◽  
Significant Interest ◽  
National League ◽  
Better Than

The Traveling Tournament Problem (TTP) is concerned with finding a double round-robin tournament schedule that minimizes the total distances traveled by the teams. It has attracted significant interest recently since a favorable TTP schedule can result in significant savings for the league. This paper proposes an original evolutionary algorithm for TTP. We first propose a quick and effective constructive algorithm to construct a Double Round Robin Tournament (DRRT) schedule with low travel cost. We then describe an enhanced genetic algorithm with a new crossover operator to improve the travel cost of the generated schedules. A new heuristic for ordering efficiently the scheduled rounds is also proposed. The latter leads to significant enhancement in the quality of the schedules. The overall method is evaluated on publicly available standard benchmarks and compared with other techniques for TTP and UTTP (Unconstrained Traveling Tournament Problem). The computational experiment shows that the proposed approach could build very good solutions comparable to other state-of-the-art approaches or better than the current best solutions on UTTP. Further, our method provides new valuable solutions to some unsolved UTTP instances and outperforms prior methods for all US National League (NL) instances.

scholarly journals Fighting Together against the Pandemic: Learning Multiple Models on Tomography Images for COVID-19 Diagnosis

AI ◽  
2021 ◽  
Vol 2 (2) ◽  
pp. 261-273
Author(s):  
Mario Manzo ◽  
Simone Pellino
Keyword(s):  
Network Architecture ◽  
State Of The Art ◽  
Ensemble Classification ◽  
Effective Vaccine ◽  
Rt Pcr ◽  
Neural Network Architecture ◽  
Experimental Phase ◽  
Different Types ◽  
Polymerase Chain ◽  
Better Than

COVID-19 has been a great challenge for humanity since the year 2020. The whole world has made a huge effort to find an effective vaccine in order to save those not yet infected. The alternative solution is early diagnosis, carried out through real-time polymerase chain reaction (RT-PCR) tests or thorax Computer Tomography (CT) scan images. Deep learning algorithms, specifically convolutional neural networks, represent a methodology for image analysis. They optimize the classification design task, which is essential for an automatic approach with different types of images, including medical. In this paper, we adopt a pretrained deep convolutional neural network architecture in order to diagnose COVID-19 disease from CT images. Our idea is inspired by what the whole of humanity is achieving, as the set of multiple contributions is better than any single one for the fight against the pandemic. First, we adapt, and subsequently retrain for our assumption, some neural architectures that have been adopted in other application domains. Secondly, we combine the knowledge extracted from images by the neural architectures in an ensemble classification context. Our experimental phase is performed on a CT image dataset, and the results obtained show the effectiveness of the proposed approach with respect to the state-of-the-art competitors.

Sign in / Sign up

Export Citation Format

Share Document