We propose UCT-Grid Area Search (UCT-GAS), which is an efficient optimization method that roughly estimates specific values in areas, and consider exploration and exploitation in optimization problems. This approach d...
详细信息
We propose UCT-Grid Area Search (UCT-GAS), which is an efficient optimization method that roughly estimates specific values in areas, and consider exploration and exploitation in optimization problems. This approach divides the search space and imagines it to be a multi-armed bandit, which enables us to use bandit algorithms to solve mathematical programming problems. Although the search speed is fast than other search algorithm like differential evolution, it might converge to a local solution. In this study, we improve this algorithm by replacing its random search part with differential evolution after several searches. Comparative experiments confirmed the search ability of the optimal solution, and our method benefits by showing that it avoids falling into a local solution and that its search speed is fast.
We present a fast method for finding optimal parameters for a low-resolution (threading) force field intended to distinguish correct from incorrect folds for a given protein sequence. In contrast to other methods, the...
详细信息
We present a fast method for finding optimal parameters for a low-resolution (threading) force field intended to distinguish correct from incorrect folds for a given protein sequence. In contrast to other methods, the parameterization uses information from >10(7) misfolded structures as well as a set of native sequence-structure pairs. In addition to testing the resulting force field's performance on the protein sequence threading problem, results are shown that characterize the number of parameters necessary for effective structure recognition.
Gross domestic product (GDP) can well reflect the development of the economy, and predicting GDP can help better grasp the future economic trends. In this article, three different neural network models, the genetic al...
详细信息
Gross domestic product (GDP) can well reflect the development of the economy, and predicting GDP can help better grasp the future economic trends. In this article, three different neural network models, the genetic algorithm - back-propagation neural network model, the particle swarm optimization (PSO) - Elman neural network (Elman NN) model, and the bat algorithm - long short-term memory model, were analyzed based on neural networks. The GDP data of Sichuan province from 1992 to 2020 were collected to compare the performance of the three models in predicting GDP. It was found that the mean absolute percentage error values of the three models were 0.0578, 0.0236, and 0.0654, respectively;the root-mean-square error values were 0.0287, 0.0166, and 0.0465, respectively;and the PSO-Elman NN model had the best performance in GDP prediction. The experimental results demonstrate that neural networks were reliable in predicting GDP and can be used for further applications in practice.
Methods relying on a single dynamic parameter to estimate the material density for the compaction quality testing of earth-rock dams and roadbed projects, present certain limitations in terms of applicability, testing...
详细信息
Methods relying on a single dynamic parameter to estimate the material density for the compaction quality testing of earth-rock dams and roadbed projects, present certain limitations in terms of applicability, testing accuracy, and work efficiency. The theory of elastic wave propagation reveals that the compaction density of the medium results from the combined interaction of multiple material properties. This study proposes a method that utilizes the transient surface wave method and a vehicle-mounted Falling Weight Deflectometer (FWD) to jointly enhance the accuracy of soil and rock material compaction detection. The transient surface wave method is employed to extract surface wave velocity and compressional wave velocity. The analysis of the FWD signal involves extracting dynamic parameters closely related to material density, including stiffness coefficients, central frequencies, and stiffness impedances, from time-domain, frequency-domain, and mechanical impedance analyses. A fully connected deep neural network is introduced to intelligently estimate the compaction density. The deep learning model is optimized by selecting the optimal activation function and optimization algorithm, as well as additional tuning. Extensive testing shows that deep learning model produce results closely approximating the true compaction density values. The average relative errors for the wet density and the dry density are 2.9% and 2.85%, respectively, meeting the quality control requirements for density testing. The proposed approach enables rapid detection and control of the compaction quality of soil and rock materials, providing a new method for the in-situ rapid detection of compaction quality.
The topic of load balanced task scheduling has emerged as a prominent and intricate area of study within the realm of Cloud computing. Swarm intelligence-based meta-heuristic algorithms are commonly considered more su...
详细信息
The topic of load balanced task scheduling has emerged as a prominent and intricate area of study within the realm of Cloud computing. Swarm intelligence-based meta-heuristic algorithms are commonly considered more suitable for the purposes of Cloud scheduling and load balancing. These algorithms employ a combination of local and global search strategies in order to ascertain the ideal location. To achieve an optimal mapping strategy for task allocation to resources, it is imperative to find a suitable equilibrium between local and global search techniques, since this approach has demonstrated significant efficacy. This research introduces a new approach to task scheduling using the Autodidactic Interactive School optimization algorithm (IASOA). The objective of this method is to decrease the time required for job execution while also enhancing throughput. The assessment of the suggested methodology has been executed, and a comparative analysis has been performed with five established algorithms in relation to makespan and throughput. The tests were subsequently extended to encompass a comparative analysis of the suggested methodology alongside four other established meta-heuristic scheduling methodologies. The study of the simulated experimentation reveals that the proposed approach yielded noteworthy advantages in makespan and throughput, with improvements of up to 10% and 60% respectively.
In modern buildings, the position(s) of elevator system(s) tends to be a crucial factor for the unimpeded vertical and on-floor circulation of their residents. The present paper introduces a method that correlates cir...
详细信息
In modern buildings, the position(s) of elevator system(s) tends to be a crucial factor for the unimpeded vertical and on-floor circulation of their residents. The present paper introduces a method that correlates circulation data for the population of a typical office building (size, density and possibility for elevator use) with structural and architectural data of each one of its floors (net usable space, circulation space, structural intrusions, etc.). The method provides an optimum position for the elevator system hoistway(s) so that all walking distances on all floors between the elevator system and usable spaces are as small as possible. Every single floor of the building is partitioned into cells that form a grid covering its surface. An index of the intensity of elevator utilization (EUII) is introduced, defined as a function of the data mentioned above. Then, Euclidean norms, based on (EUII) values, provide weighted mean distances for locating the point on the vertical projection of the building that corresponds to the minimal mean distance from every cell of its usable spaces. A case study of a typical office building served by a single elevator system exemplifies the proposed approach, initially for a single floor and then for all the floors of the building.
暂无评论