摘要 :
The purpose of this paper is to apply convolutional neural networks to help diagnose patients with kidney disease. Findings are divided into four types: kidney tumor, cyst, normal and stones. Currently large numbers of people enga...
展开
The purpose of this paper is to apply convolutional neural networks to help diagnose patients with kidney disease. Findings are divided into four types: kidney tumor, cyst, normal and stones. Currently large numbers of people engage in unhealthy lifestyles with poor diet, sedentary activity, and insufficient sleep, often resulting in kidney disease. Early detection is necessary so preventative actions can be taken to help the kidneys recover. Traditional detection is complex and imprecise, while computational diagnosis promises more rapid and accurate results. Convolutional Neural Networks (CNN), part of deep learning, are appropriate diagnostic tools already being used in medical image identification and disease classification. Here we show CNN diagnosis with ultimate training accuracies up to 98% and test accuracies up to 99%.
收起
摘要 :
Aiming at small objects detection such as unmanned aerial vehicle (UAV), this paper proposes a fast object detection
algorithm based on depthwise separable convolutions. Firstly, the inverted residuals units based on depthwise con...
展开
Aiming at small objects detection such as unmanned aerial vehicle (UAV), this paper proposes a fast object detection
algorithm based on depthwise separable convolutions. Firstly, the inverted residuals units based on depthwise convolutions
and pointwise convolutions are used to construct a lightweight feature extraction network to improve the network’s speed.
Secondly, the feature pyramid network is used to detect the five scale feature maps to improve the detection performance
of small objects. Otherwise, we make an UAV dataset based on the urban background for training and testing of our
experiments. The experimental results show that the improved method proposed in this paper can effectively improve the
detection accuracy and real-time performance of UAVs in complex urban backgrounds, and the computation of network is
greatly reduced, thereby making it possible to achieve object detection on embedded systems.
收起
摘要 :
Aiming at small objects detection such as unmanned aerial vehicle (UAV), this paper proposes a fast object detection
algorithm based on depthwise separable convolutions. Firstly, the inverted residuals units based on depthwise co...
展开
Aiming at small objects detection such as unmanned aerial vehicle (UAV), this paper proposes a fast object detection
algorithm based on depthwise separable convolutions. Firstly, the inverted residuals units based on depthwise convolutions
and pointwise convolutions are used to construct a lightweight feature extraction network to improve the network’s speed.
Secondly, the feature pyramid network is used to detect the five scale feature maps to improve the detection performance
of small objects. Otherwise, we make an UAV dataset based on the urban background for training and testing of our
experiments. The experimental results show that the improved method proposed in this paper can effectively improve the
detection accuracy and real-time performance of UAVs in complex urban backgrounds, and the computation of network is
greatly reduced, thereby making it possible to achieve object detection on embedded systems.
收起
摘要 :
Large-scale wind power integration has exerted negative influence on the power system, because of the intermittency and anti-peak-regulation of wind power. High-energy consuming large industry consumers for large-scale wind power ...
展开
Large-scale wind power integration has exerted negative influence on the power system, because of the intermittency and anti-peak-regulation of wind power. High-energy consuming large industry consumers for large-scale wind power integration improvement theory is presented. Large industry consumers to can have a powerful consuming wind power by increasing the appropriate device input and taking appropriate management and technical measures. Taking the Gansu power system as example, the results show that by way of high-energy consuming, the peak-regulation of system can be improved, and the conclusion can provide scientific basis for the power system dispatchers.
收起
摘要 :
This paper describes a stepped switching controllable high voltage shunt reactor's basic operating principle, the device can regulate the system reactive power, voltage and frequency over inhibition of arc current, with a continuo...
展开
This paper describes a stepped switching controllable high voltage shunt reactor's basic operating principle, the device can regulate the system reactive power, voltage and frequency over inhibition of arc current, with a continuous smooth power adjustable harmonic current small and the advantages of fast response. It analyzes the stepped switching controllable high voltage shunt reactor protection features and functionality, protection and circuit breaker protection, Article uses Fourier series decomposition method. This method analyzed about current harmonic content of 300Mvar 750kV controllable high voltage shunt reactor's work winding which will put into operation in Hexi 750kV transmission project Dunhuang substation.
收起
摘要 :
A novel method of deriving the electromagnetic dyadic Green's functions in an unbounded, lossless, reciprocal and homogeneous chiral medium described by the constitutive relations D = εE + jγB and H = jγE + μ~(-1) B -(ωε)~(-...
展开
A novel method of deriving the electromagnetic dyadic Green's functions in an unbounded, lossless, reciprocal and homogeneous chiral medium described by the constitutive relations D = εE + jγB and H = jγE + μ~(-1) B -(ωε)~(-1) γJ is given. The diveigenceless and irrotational splitting of dyadic Dirac δ function and Fourier's transformation are used to obtain the divergenceless and irrotational component of dyadic Green's functions in spectral domain with a chiral medium.
收起
摘要 :
A novel method of deriving the electromagnetic dyadic Green's functions in an unbounded, lossless, reciprocal and homogeneous chiral medium described by the constitutive relations D = εE + jγB and H = jγE + μ~(-1) B - (ωε)~(...
展开
A novel method of deriving the electromagnetic dyadic Green's functions in an unbounded, lossless, reciprocal and homogeneous chiral medium described by the constitutive relations D = εE + jγB and H = jγE + μ~(-1) B - (ωε)~(-1) γJ is given. The diveigenceless and irrotational splitting of dyadic Dirac δ function and Fourier's transformation are used to obtain the divergenceless and irrotational component of dyadic Green's functions in spectral domain with a chiral medium.
收起