This paper presents an all-solid porous Ag/AgCl electric field sensor with ultralow-potential drift for detecting the seafloor electric field signals. The superiority of porous electrode compared with flat electrode o...
详细信息
This paper presents an all-solid porous Ag/AgCl electric field sensor with ultralow-potential drift for detecting the seafloor electric field signals. The superiority of porous electrode compared with flat electrode on the polarization stability is expounded, and the technological process using solid state agglomeration in developing the all-solid porous Ag/AgCl electrode core are described. Moreover, a new sensor shell is proposed. Numerous parameters, e.g., polarization resistance, self-potential, drift, etc., of the proposed electrode are tested. The experimental results show that the self-potential is less than ±0.1 mV, the source resistance is less than 0.01H, and the drift potential is less than ±5μV/24h, which indicate the superior performance of the proposed Ag/AgCl electric field sensor for marine electric field exploration.
Due to the unknown complexity of geological conditions, drilling operations are difficult to carry out. It is of great value to implement drilling measurement while drilling. However, due to the poor working condition...
详细信息
Due to the unknown complexity of geological conditions, drilling operations are difficult to carry out. It is of great value to implement drilling measurement while drilling. However, due to the poor working conditions underground, information transmission for the drilling process may be affected, which leads to the loss and conflicts of the data. It is necessary to use effective method to deal with the data and to make evaluation for the drilling process. In this paper, we present a D-S data fusion method and use fused data to form a framework to evaluate efficiency for the drilling process. We can efficiently analyze the entire drilling process and optimize the drilling parameters based on this framework.
In this paper, a fractional order genetic regulatory network system(GRNs) with delay is considered. Firstly, the stability is investigated and the conditions of the existence for Hopf bifurcation are attained by ana...
详细信息
In this paper, a fractional order genetic regulatory network system(GRNs) with delay is considered. Firstly, the stability is investigated and the conditions of the existence for Hopf bifurcation are attained by analyzing it’s characteristic equation. Then combining the analysis we can derive that the fractional order GRNs will generate Hopf bifurcation as the GRNs with specific parameter values. A fractional PD controller can be used to control the bifurcation behaviors of the delayed fractional order GRNs. Finally, some numerical examples are exploited to illustrate the validity of theoretical analysis.
With the increased number of traffic accidents, the research and development of smart cars have been promoted. The detection of street objects has become one of the important research topics. Generic Model detection a...
详细信息
With the increased number of traffic accidents, the research and development of smart cars have been promoted. The detection of street objects has become one of the important research topics. Generic Model detection algorithm based on Convolution Neural Network(CNN) need to design the training model, while the training and testing of the model will take a lot of time. Transfer Learning is used to fine-tune the pre-trained models, using the Image task datasets of COCO, transferring a generic deep learning model to specific one with different weights and outputs. Furthermore, the CNN structure is adjusted to improve overall performance, and the street environment is trained to the special scene. We compare the results of experiments, and the results showed that the network which is fine-tuned is effective.
In the ultrasonic nondestructive testing, the echo signal is polluted by noise and the signal-to-noise ratio is low. To solve the problem, a new wavelet thresholding function is introduced in this paper based on soft ...
详细信息
In the ultrasonic nondestructive testing, the echo signal is polluted by noise and the signal-to-noise ratio is low. To solve the problem, a new wavelet thresholding function is introduced in this paper based on soft and hard thresholding functions. Compared with the existing improved thresholding functions, the new thresholding function is simple in computation and continuous and easy to adjust, it is suitable for some kinds of mathematical disposals. The simulation results show that the new thresholding function can suppress the noise effectively, it is better than soft and hard thresholding functions and the existing improved thresholding functions and has high practical value.
The classification of hyperspectral images(HSIs) is a hot topic in the field of remote sensing technology. In recent years, convolutional neural network(CNN) has achieved great success for HSI classification. However,...
详细信息
The classification of hyperspectral images(HSIs) is a hot topic in the field of remote sensing technology. In recent years, convolutional neural network(CNN) has achieved great success for HSI classification. However, CNN has to do a great effort in parameters tuning which is time-consuming. Furthermore, a large number of samples are required to train CNN,nevertheless, it is expensive to obtain enough training samples from HSIs. In this paper, we propose a novel classification approach based on deep forest. To reduce the dimension of hyperspectral data, principal component analysis(PCA) is performed during the pre-processing. In contrast to the CNN, our method has fewer hyper-parameters and faster training speed. To the best of our knowledge, this is among the first deep forest-based hyperspectral spectral information classification. Extensive experiments are conducted on two real-world HSI datasets to show the proposed method is significantly superior to the state-ofthe-art methods.
High accurate rate of street objects detection is significant to realize intelligent vehicles. Algorithms based on Convolution Neural Network (CNN) have already shown their reasonable performance on general object det...
详细信息
High accurate rate of street objects detection is significant to realize intelligent vehicles. Algorithms based on Convolution Neural Network (CNN) have already shown their reasonable performance on general object detection. For example SSD and YOLO can detection wide variety of objects on 2D images in real time, but the performance is not good enough on street objects detection especially on complex urban street environment. In this paper, instead of proposing and training a new CNN model, we use transfer learning methods to learn from generic CNN model to our specific model to achieve good performance. The transfer learning methods include fine-tuning the pretrained CNN model with self-made dataset and adjusting CNN model structure. We analyze transfer learning results on fine-tuning Single shot multibox detector (SSD) with self-made datasets. The experimental results based on transfer learning method show that the proposed method is effective.
Affective computing plays a key role in music artificial intelligence, in which a music emotion classification model is indispensable. Both discrete classification model and continuous dimensional model are commonly u...
详细信息
Affective computing plays a key role in music artificial intelligence, in which a music emotion classification model is indispensable. Both discrete classification model and continuous dimensional model are commonly used for music emotion classification. However, these models are not designed in views of composers, which is insufficient for the perception of music emotion. In this paper, a fuzzy music emotion classification model is proposed by extracting the music expression marks considering the composers emotion. Experiments on subjective evaluation in the feeling of pleasure and arousal according to the change of three selected features(i.e., tempo, register, and dynamic) are conducted by listeners from different subjects. The experimental results show that the correlation between the proposal fuzzy model and the the results from questionnaires reaches 80% on average, which demonstrate the validity of the proposed fuzzy music emotion classification model. The proposal could be applied to music emotion generation conveyed from either composers or players, and to emotion recognition of music as for audiences.
Piezoelectric geophones are vibration detectors that convert vibration acceleration signals into electrical signals. High performance piezoelectric materials can improve the sensitivity of piezoelectric geophone and m...
详细信息
Piezoelectric geophones are vibration detectors that convert vibration acceleration signals into electrical signals. High performance piezoelectric materials can improve the sensitivity of piezoelectric geophone and meet the need of high-resolution seismic data acquisition. The comprehensive performance of relaxor piezoelectric single crystal PMN-PT is more superior than PZT, and it is potential to be applied to high sensitivity and small volume geophones. In this paper, the central compressed geophone core model based on PMN-PT was established and theoretically analyzed. Then, a multiphysics simulation model was set up in COMSOL for simulation calculation. Finally, experimental verification was carried out. The results show that using PMN-PT in geophone core design can improve the sensitivity of the model by more than 120% compared with the traditional PZT material. The PMN-PT has the potential to be applied to high sensitivity and small volume geophones.
Compared with speech, facial expression, and body languages, Electroencephalogram (EEG) can reflect the inner activity of brain, by which the emotion can be recognized objectively and naturally. In this paper, an EEG ...
详细信息
Compared with speech, facial expression, and body languages, Electroencephalogram (EEG) can reflect the inner activity of brain, by which the emotion can be recognized objectively and naturally. In this paper, an EEG emotion recognition system is proposed in which EEG signals of 6 channels are detected from Frontal Lobe and Temporal Lobe, and then the time-domain features of statistics features and frequency-domain features of spectrum centroid (SC) are extracted. To remove the redundant feature, Linear Discriminant Analysis (LDA) is used to reduce the dimension of feature. In addition, an improved classifier based on PSO-SVM is applied to classify the emotional states in the Valance-Arousal emotion model, respectively, which are defined as High-Valance (HV) and Low-Valance (LV) on the Valance dimension and High-Arousal (HA) and Low-Arousal (LA) on the Arousal dimension. EEG emotion recognition experiment on DEAP dataset is performed, from which the results show that the proposed method obtains the accuracies of 73.33% on Valance dimension and 72.78% on Arousal dimension, which are higher than those of some state-of-the art works.
暂无评论