Adaptive weights learning in CNN feature fusion for crime scene investigation image classification

Liu, Ying; Zhang, Nan; Ping, Wang Fu; Kiang, Chiew Tuan; Pang, Lim Keng; Chang, Zhang; Lü, Chao; Lü, Jun; Ling, Nam

doi:10.1080/09540091.2021.1875987

Cited by 37 publications

(21 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each convolution group introduces 4 3×3 convolution layers and 2 max-pooling layers and then adds a batch normalization layer (BN layer), which can speed up the convergence of the model.The convolutional layers are supplemented with 0 to prevent edge pixels from being omitted when the convolution kernel performs convolution calculations. Using dropout regularization, all neurons are discarded according to the probability of 0.3, which simplifies the entire network model, suppresses overfitting, and further improves the classification ability of the model [ 25 ].…”

Section: Network Improvementsmentioning

confidence: 99%

“…e convolutional layers are supplemented with 0 to prevent edge pixels from being omitted when the convolution kernel performs convolution calculations. Using dropout regularization, all neurons are discarded according to the probability of 0.3, which simplifies the entire network model, suppresses overfitting, and further improves the classification ability of the model [25].…”

Section: Network Improvementsmentioning

confidence: 99%

See 1 more Smart Citation

Decision-Making Application of the Cloud-Fog Hybrid Model Based on the Improved Convolutional Neural Network in Financial Services in Smart Medical Care

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In order to alleviate the “difficulty in seeing a doctor” for the masses, continuously optimize the service process, and explore new financial service processes for admission and discharge, this study proposes a cloud-fog hybrid model UCNN-BN based on an improved convolutional neural network and applies it to financial services in smart medical care. Decision-making applications: this research improves and designs the UCNN network based on AlexNet and introduces small convolution layers to form convolution groups, making the network more adjustable. The network structure is simpler and more flexible, and it is easy to adjust the algorithm. The number of parameters is small, and it can be directly superimposed without having to add new network hidden layers. The experimental results show that the recognition rate of the UCNN network on the FER2013 and CK+ datasets is higher than that of other recognition methods, and the recognition rates on the FER2013 and CK+ datasets are 98% and 68.01%, due to other methods. This shows that the improved convolutional neural network used in this study for financial services in smart medical care has certain applicability, and small convolution kernels help to extract more subtle features, so as to identify more accurately.

show abstract

Section: Network Improvementsmentioning

confidence: 99%

Section: Network Improvementsmentioning

confidence: 99%

Decision-Making Application of the Cloud-Fog Hybrid Model Based on the Improved Convolutional Neural Network in Financial Services in Smart Medical Care

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…In recent years, sports artificial intelligence research, the main subject is computer science, and the algorithm empirical research of basic theory is preferred [ 5 ]. It mainly involves the use of neural network-based machine learning-related algorithms, involving sports performance prediction [ 6 ], human action recognition and evaluation [ 7 ], technical and tactical decision support, sports injury assessment, etc.…”

Section: Introductionmentioning

confidence: 99%

Application of Improved VMD-LSTM Model in Sports Artificial Intelligence

Zhang

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In recent years, with the rapid development of a new generation of artificial intelligence technology, how to deeply apply artificial intelligence technology to physical education and break through the limitations of time-space scenarios and knowledge transfer methods in traditional models has become a key issue in intelligent physical education in the era of artificial intelligence. In order to realize the online monitoring of wearable devices with artificial intelligence in sports and overcome the problem of low recognition accuracy of electrocardiogram, blood oxygen, and respiratory signals in many cases, this paper proposes a combination of variational modal decomposition based on the maximum envelope kurtosis method. Long-short-term neural network (VMD-LSTM) monitoring method for wearable sports equipment. Through experimental analysis and verification, the current signal of the VMD model shows a trend of fluctuating from large to stable and then to large with motion, while the training accuracy of LSTM after the 150th iteration is 94.09%, which shows that the coupling model VMD LSTM can better predict the direction of sports artificial intelligence. In addition, although the training time of the BP neural network is shorter than that of the LSTM model, there is a large gap between the recognition effect and the LSTM, and there are also large differences between different neural network structures. This shows that the VMD-LSTM model has broad application prospects in such models.

show abstract

“…The phase distribution contains exp(ilθ) term, θ is the rotation azimuth and l is the topological charge. When the vortex light propagates along the positive direction of the Z axis, the complex amplitude E 1 of the electric field on the observation surface (Ying et al, 2021) with Z 0 can be expressed as:…”

Section: Principle Of Light Interference In Sensing Systemmentioning

confidence: 99%

Light intensity optimization of optical fiber stress sensor based on SSA-LSTM model

Qiao

Wang

2022

Front. Energy Res.

View full text Add to dashboard Cite

In order to further improve the measurement range and accuracy of optical fiber stress sensor based on the interference between rising vortex beam and plane wave beam, a new stress demodulation model is designed. This model proposes a method to optimize the long-term and short-term memory network (LSTM) model by using sparrow search algorithm (SSA), extract the main characteristics of the influence of various variables on optical fiber stress sensor, and fit the relationship between sensor stress and beam phase difference. This method is an attempt of the deep learning model LSTM in the study of stress mediation model. There are very few related studies, and it is very necessary to fill this gap. In the experiment, the SSA-LSTM neural network is trained by using the data of stress and phase difference measured by the optical fiber stress sensor. The test results show that the mean error of SSA-LSTM neural network is less than that of LSTM neural network, which shows that the combination of SSA-LSTM model and optical fiber stress sensor can make its measurement accuracy higher, The algorithm can more effectively reduce the influence of the surrounding environment and the influence of the light source fluctuation on the measurement range and accuracy of the optical fiber sensor, and has good practical application value. It is proved that the deep learning LSTM neural network has good application value in the light intensity optimization of optical fiber stress sensor.

show abstract

Adaptive weights learning in CNN feature fusion for crime scene investigation image classification

Cited by 37 publications

References 21 publications

Decision-Making Application of the Cloud-Fog Hybrid Model Based on the Improved Convolutional Neural Network in Financial Services in Smart Medical Care

Decision-Making Application of the Cloud-Fog Hybrid Model Based on the Improved Convolutional Neural Network in Financial Services in Smart Medical Care

Application of Improved VMD-LSTM Model in Sports Artificial Intelligence

Light intensity optimization of optical fiber stress sensor based on SSA-LSTM model

Contact Info

Product

Resources

About