相关实验视频
Updated: Jan 23, 2026

05:16
Flying Insect Detection and Classification with Inexpensive Sensors
Published on: October 15, 2014
25.7K
使用卷积神经网络的过渡边缘传感器的信号和背景触发器的二元分类
Elmeri Rivasto1, Katharina-Sophie Isleif2, Friederike Januschek3
1CP3-origins, Department of Physics, Chemistry and Pharmacy, University of Southern Denmark, Campusvej 55, 5230, Odense, Denmark. rivasto@cp3.sdu.dk.
Scientific reports
|January 21, 2026
概括
卷积神经网络 (CNN) 在任何光粒子搜索II (ALPS II) 实验中进行了测试,以检测轴子. 由于背景噪声,CNNs的表现并没有超过传统方法,这表明未来的研究应该专注于数据结构.
科学领域:
- 粒子物理学 粒子物理学
- 实验物理实验物理学
- 机器学习 机器学习
背景情况:
- 任何光粒子搜索II (ALPSII) 实验使用1064nm激光搜索轴子和轴子类粒子.
- 基于低温过渡边缘传感器 (TES) 的单光子探测器计划增强ALPS II的检测能力,需要10-24W的灵敏度.
研究的目的:
- 在ALPS II实验中调查卷积神经网络 (CNN) 作为二元分类器的有效性,以区分光子触发的脉冲和背景噪声.
- 评估CNN的性能与已建立的基于切割的分析方法来检测弱信号.
主要方法:
- 训练CNN模型从实验数据中分类1064nm光子触发脉冲 (光) 与背景脉冲 (暗).
- 为CNN二进制分类器进行了严格的超参数优化.
- 将CNN方法的检测意义与之前优化的基于切割的分析进行了比较.
主要成果:
- 基于CNN的二进制分类器没有超过优化的基于切割的分析的检测意义.
- 接近1064nm的背景黑体光子触发显著限制了CNN的性能,因为训练混乱.
- 纤维合黑体辐射被证实是主要的限制背景源.
结论:
- 在目前的二进制分类配置中,由于背景干扰,CNN对于这个特定的TES数据集并不优于基于切割的方法.
- 未来的研究应该考虑基于回归的CNN,并优先考虑标准化,结构良好的训练数据,而不是广泛的超参数调整.
- 这些发现适用于任何用于分析信号检测的单变时间序列数据的设备.
相关概念视频
Classification of Signals
1.3K
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
1.3K
Convolution: Math, Graphics, and Discrete Signals
874
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
874
Convolution Properties II
583
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
583
Binary Fission
2.5K
Binary fission is the primary mode of asexual reproduction in prokaryotes, such as bacteria. It results in the production of two genetically identical daughter cells. This highly efficient process ensures the rapid propagation of bacterial populations under favorable conditions and involves coordinated cellular and molecular events.DNA Replication and SeparationThe process begins with the replication of the bacterial chromosome. The circular DNA molecule unwinds at a specific origin of...
2.5K
Binary Fission
63.0K
Fission is the division of a single entity into two or more parts, which regenerate into separate entities that resemble the original. Organisms in the Archaea and Bacteria domains reproduce using binary fission, in which a parent cell splits into two parts that can each grow to the size of the original parent cell. This asexual method of reproduction produces cells that are all genetically identical.
63.0K
Cooperative Allosteric Transitions
8.6K
Cooperative allosteric transitions can occur in multimeric proteins, where each subunit of the protein has its own ligand-binding site. When a ligand binds to any of these subunits, it triggers a conformational change that affects the binding sites in the other subunits; this can change the affinity of the other sites for their respective ligands. The ability of the protein to change the shape of its binding site is attributed to the presence of a mix of flexible and stable segments in the...
8.6K

