全文获取类型
收费全文 | 6904篇 |
免费 | 1219篇 |
国内免费 | 428篇 |
专业分类
化学 | 2128篇 |
晶体学 | 33篇 |
力学 | 559篇 |
综合类 | 253篇 |
数学 | 2477篇 |
物理学 | 3101篇 |
出版年
2024年 | 5篇 |
2023年 | 133篇 |
2022年 | 254篇 |
2021年 | 326篇 |
2020年 | 254篇 |
2019年 | 197篇 |
2018年 | 149篇 |
2017年 | 254篇 |
2016年 | 316篇 |
2015年 | 236篇 |
2014年 | 442篇 |
2013年 | 567篇 |
2012年 | 475篇 |
2011年 | 430篇 |
2010年 | 416篇 |
2009年 | 474篇 |
2008年 | 456篇 |
2007年 | 464篇 |
2006年 | 381篇 |
2005年 | 301篇 |
2004年 | 244篇 |
2003年 | 263篇 |
2002年 | 235篇 |
2001年 | 182篇 |
2000年 | 185篇 |
1999年 | 137篇 |
1998年 | 126篇 |
1997年 | 121篇 |
1996年 | 105篇 |
1995年 | 63篇 |
1994年 | 70篇 |
1993年 | 71篇 |
1992年 | 35篇 |
1991年 | 31篇 |
1990年 | 32篇 |
1989年 | 15篇 |
1988年 | 15篇 |
1987年 | 10篇 |
1986年 | 20篇 |
1985年 | 16篇 |
1984年 | 13篇 |
1982年 | 6篇 |
1981年 | 7篇 |
1979年 | 4篇 |
1977年 | 5篇 |
1975年 | 1篇 |
1972年 | 1篇 |
1971年 | 1篇 |
1967年 | 1篇 |
1959年 | 4篇 |
排序方式: 共有8551条查询结果,搜索用时 15 毫秒
1.
全连接网络作为深度学习中的一种典型结构,几乎在所有神经网络模型中均有出现。在近红外光谱定量分析中,光谱数据样本数量较少,但每个样本的维度高。导致了两个问题:将光谱直接输入网络,网络的参数量会十分庞大,训练模型需要更多的样本,否则模型容易进入过拟合状态;在输入网络前对光谱进行降维,虽解决了网络参数量过大的问题,但会丢失一部分信息,无法充分发挥网络的学习能力。针对近红外光谱的特性,提出了一种分组全连接的近红外光谱定量分析网络GFCN。该网络在传统的两层全连接网络的基础上,用若干个小的全连接层替代第一个全连接层,克服了直接输入光谱导致网络参数量过大的缺点。采用Tecator和IDRC2018数据集对该方法进行测试,同时与全连接网络FCN和偏最小二乘PLS两种方法进行对比。结果显示:在两个数据集上,GFCN预测效果均优于FCN和PLS。在只有少量样本参与建模的情况下,GFCN依然能够保持较高的预测效果。表明,GFCN可以用于近红外光谱的定量分析,并且适应样本较少的场景,具有重要的研究价值和广泛的应用场景。 相似文献
2.
3.
Ryosuke Yano 《理论物理通讯》2022,74(4):45601
The crowd evacuation of pairs of pedestrians (i.e. pairs consisting of a parent and a child) is numerically investigated. Here, it is assumed that all pedestrians have their own partners, and move randomly inside the bounded domain of the right-hand room as an initial state. All pedestrians start their evacuations after they contact their partners. The evacuations are completed by the transfer of all the pairs from the right-hand room to the left-hand room through an exit. A frozen swarm tends to appear in the right-hand room as the total number of pedestrians increases. The frozen swarm moves without changing its form, unless it is dissolved by a strong collision with a pair of pedestrians that comes back from the left-hand room by accident. Finally, the evacuation speed also depends on the area of the Escape Zone, whereas an obstacle placed in front of an exit also changes the speed of the evacuation in accordance with the type of motion of the children. 相似文献
4.
为克服机器学习方法在油藏单井产量预测中的过拟合问题, 提高油田生产中的产量预测精度, 提出一种基于条件生成式对抗网络(CGAN)的油藏单井产量预测模型。该模型使用长短期记忆、全连接等基础神经网络, 构建生成和判别网络模型。生成网络模型以产量影响因素为条件输入, 生成预测产量数据, 利用对数损失函数评价预测数据与真实数据之间的偏差, 通过条件生成式对抗网络的博弈训练, 并结合贝叶斯超参数优化算法, 优化模型结构, 综合提高模型的泛化能力。基于Eclipse数值模拟软件建立同一井网条件下不同地质和生产条件下的油藏单井产量数据库, 以地质与生产条件等产量影响因素作为模型的条件输入, 进行油藏单井产量预测。结果表明: 与全连接神经网络(FCNN)、随机森林(RF)以及长短期记忆神经网络(LSTM)模型的预测结果相比, CGAN模型在测试集上的平均绝对百分比误差分别提升了2.59%、0.81%以及1.72%, 并且过拟合比最小(1.027)。说明CGAN降低了机器学习产量预测模型的过拟合程度, 提高了模型的泛化能力与预测精度, 验证了所提算法的优越性, 对指导油田高效开发和保障我国能源战略安全具有重要意义。 相似文献
5.
深度学习在检测领域高速发展,但受限于训练数据和计算效率,在基于嵌入式平台的边缘计算领域,尤其是实时跟踪应用中深度学习的智能化算法应用并不广泛。针对这一现象,同时为满足现阶段国产化、智能化的技术需求,提出了一种改进的孪生网络深度学习跟踪算法。在特征网络加入微调网络,解决了网络模型无法在线更新的问题,提升了跟踪的准确性;在IoUNet损失函数中加入中心距离惩罚项,解决了IoUNet当IoU相同时位置跳跃,存在收敛盲区和收敛速度慢的问题;将训练后的网络通过通道剪枝,缩减网络模型尺寸,提升了模型加载和运行的速度。在华为Atlas200NPU平台上实现了实时运行,算法准确率高达0.90(IoU>0.7),帧率达到66 Hz。 相似文献
6.
为优化众包物流服务质量,考虑平台罚金政策,构建了包括发包方、众包平台和接包方在内的三层众包物流服务网络模型,并进行算例分析。结果表明,众包平台实施罚金政策并加大自身服务质量投入成本会促使接包方改善自身的服务质量,众包平台的服务质量和利润随之增大,但一味的增大罚金不但会使得接包方利润下降,众包平台的服务质量和利润也呈稍微下降趋势,因此平台应该选择合适的罚金区间;平台在竞争的同时也要进行一定的合作,因为平台间同步协调改进罚金政策以及质量投入会取得更大的收益和更高的平均服务质量。 相似文献
7.
Force-constant-decayed anisotropic network model: An improved method for predicting RNA flexibility 下载免费PDF全文
Wei-Bu Wang 《中国物理 B》2022,31(6):68704-068704
RNA is an important biological macromolecule, which plays an irreplaceable role in many life activities. RNA functions are largely determined by its tertiary structure and the intrinsic dynamics encoded in the structure. Thus, how to effective extract structure-encoded dynamics is of great significance for understanding RNA functions. Anisotropic network model (ANM) is an efficient method to investigate macromolecular dynamical properties, which has been widely used in protein studies. However, the performance of the conventional ANM in describing RNA flexibility is not as good as that on proteins. In this study, we proposed a new approach, named force-constant-decayed anisotropic network model (fcd-ANM), to improve the performance in investigating the dynamical properties encoded in RNA structures. In fcd-ANM, nucleotide pairs in RNA structure were connected by springs and the force constant of springs was decayed exponentially based on the separation distance to describe the differences in the inter-nucleotide interaction strength. The performance of fcd-ANM in predicting RNA flexibility was evaluated using a non-redundant structure database composed of 51 RNAs. The results indicate that fcd-ANM significantly outperforms the conventional ANM in reproducing the experimental B-factors of nucleotides in RNA structures, and the Pearson correlation coefficient between the predicted and experimental nucleotide B-factors was distinctly improved by 21.05% compared to the conventional ANM. Fcd-ANM can serve as a more effective method for analysis of RNA dynamical properties. 相似文献
8.
Ultrasound is a green technology for intensifying enzymatic reactions. In this study, an ultrasonic water bath with equipment parameters of 28 kHz, 1750.1 W/m2, 60% duty cycle was used to assist the synthesis of butyric acid-lauric acid designer lipid (BLDL), which was catalyzed by Lipozyme 435. A convincing three-layer feed-forward artificial neural network (ANN) model was established (R2 = 0.949, RMSE = 4.759, ADD = 7.329) to accurately predict the optimal parameters combination, which was described as 13.72 mL reaction volume, 15.49% enzyme loading, 0.253 substrate molar ratio (tributyrin/lauric acid), 56.58 °C reaction temperature and 120 min reaction time. The ultrasonic assistance increased actual butyric acid conversion rate by 11.38%, and also enhanced the consumption rate of tributyrin and lauric acid during the reaction. Meanwhile, the esterification activity of Lipozyme 435 was enhanced and its effectiveness up to 6 cycles. Structurally, ultrasound assistance significantly disrupted the secondary structure of the Lipozyme 435: reduced the content of α-helices, increased the content of β-sheet and β-turn. In addition, sonication caused an increase in crevice and micro-damage on the surface of the immobilized enzyme. In conclusion, low-intensity ultrasound at 28 kHz improved the synthesis efficiency of BLDL, which was scientifically predicted by ANN model, and the change of enzyme structure may be the vital reason for ultrasound enhanced reaction. However, the effect of ultrasound on immobilized enzymes’ activity needs to be further explored. 相似文献
9.
为解决单一的小波神经网络预测精度不高的问题,提出一种新的基于小波去噪和WNN-ARIMA组合模型,应用小波阈值去噪法对小波神经网络的输入值进行预处理,同时对模型残差值进行ARIMA模型修正.利用该组合模型对洮河流域下巴沟站年径流量进行预测,预测趋势和预测值与原始实测数据吻合度高,表明此组合模型可靠性强,可以有效预测年径流量,以期为洮河流域和其他流域的年径流量预测提供新方法,为水利工程建设和水资源优化配置提供依据. 相似文献
10.
Dynamics and intermittent stochastic stabilization of a rumor spreading model with guidance mechanism in heterogeneous network 下载免费PDF全文
Xiaojing Zhong 《中国物理 B》2022,31(4):40205-040205
We propose a novel rumor propagation model with guidance mechanism in heterogeneous complex networks. Firstly, the sharp threshold of rumor propagation, global stability of the information-equilibrium and information-prevailing-equilibrium under R0 <1 and R0> 1 is carried out by Lyapunov method and LaSalle's invariant principle. Next, we design an aperiodically intermittent stochastic stabilization method to suppress the rumor propagation. By using the Itô formula and exponential martingale inequality, the expression of the minimum control intensity is calculated. This method can effectively stabilize the rumor propagation by choosing a suitable perturb intensity and a perturb time ratio, while minimizing the control cost. Finally, numerical examples are given to illustrate the analysis and method of the paper. 相似文献