This paper proposes a coupling matrix element optimization method for microwave filters. The traditional method is more complex and does not directly optimize the filter coupling matrix elements. The firefly algorithm...
详细信息
This paper proposes a coupling matrix element optimization method for microwave filters. The traditional method is more complex and does not directly optimize the filter coupling matrix elements. The firefly algorithm optimization method used in this paper directly optimizes the elements of the N + 2 order coupling matrix. Compared with the traditional method, it has better speed and optimization effect. First, the elements of the specific coupling matrix are introduced into the optimization algorithm to be executed, then the matrix is iterated through the set objective function. Finally, when the optimized data is within the allowable range, the optimization of the elements of the coupling matrix is stopped and optimization is performed. The resulting coupling matrix outputs the response. To prove the effectiveness of the proposed method, three methods were used to optimize the coupling matrix elements of the fourth-order filter and compare the final optimization results.
Deep drilling is a costly project and efficiency is of paramount importance. The weight on bit is one of the main operating parameters that influences the drilling efficiency and it was controlled by manual before. Bu...
详细信息
Deep drilling is a costly project and efficiency is of paramount importance. The weight on bit is one of the main operating parameters that influences the drilling efficiency and it was controlled by manual before. But after people saw the giant potential of an auto-drilling system in increasing the drilling efficiency, more and more studies on the feed back control of weight on bit have emerged. This paper mainly studied weight on bit dynamic under the variational formation based on a lumped parameter model and a self-tuning PID controller for weight on bit control. The parameters of the PID controller are tuned by using gradient descent method and RBF neural network identification.
Optical music recognition (OMR) is an important technology to recognize paper music sheet automatically, which has been applied to preserve music scores. In this paper, we propose a real-time OMR system to recognize s...
详细信息
The resonant cavity is an important component of Overhauser magnetometer sensor. Its function is to make the working substance generate dynamic nuclear polarization effect in the sensor. An alternative design of reson...
详细信息
EEG emotion recognition based on ensemble learning is proposed, in which three classification models including k-Nearest Neighbor, Decision Tree and Logistic Regression are integrated. In feature extraction, four kind...
详细信息
Protein complexes are the key molecular entities which plays an indispensable role in our life activities. systematic identification of protein complexes is an important application of data mining in bioscience. The e...
详细信息
Protein complexes are the key molecular entities which plays an indispensable role in our life activities. systematic identification of protein complexes is an important application of data mining in bioscience. The existing computation methods of detecting protein complexes are usually based on the topological properties of protein-protein interaction(PPI) network ***, limited by the inherent single structure of the PPI network, the mining of protein complexes may not be fully *** this paper, we propose an original multi-objective optimization strategy based protein complex detection method, which is used Adaptive Multi-Objective Black Hole algorithm, called AMOBH. In the selection of objective function strategy, we integrate the topological structure of PPI network data with semantic similarity based on GO(Gene Ontology) annotation data. Experiments demonstrate that the method we adopt provide more convinced results and higher computational efficiency compared with the existing prediction measures.
To improve the accuracy of Electroencephalogram (EEG) emotion recognition, a stacking emotion classification model is proposed, in which different classification models such as XGBoost, LightGBM and Random Forest are ...
详细信息
To improve the accuracy of Electroencephalogram (EEG) emotion recognition, a stacking emotion classification model is proposed, in which different classification models such as XGBoost, LightGBM and Random Forest are integrated to learn the features. In addition, the Renyi entropy of 32 channels' EEG signals are extracted as the feature and Linear discriminant analysis (LDA) is employed to reduce the dimension of the feature set. The proposal is tested on the DEAP dataset, and the EEG emotional states are accessed in Arousal-Valence emotion space, in which HA/LA and HV/LV are classified, respectively. The result shows that the average recognition accuracies of 77.19% for HA/LA and 79.06% for HV/LV are obtained, which demonstrates that the proposal is feasible in EEG emotion recognition.
Different from previous studies on memristive chaotic oscillators which tended to adopt common mathematical models but lacked practical consideration, in this paper, a novel memristive chaotic oscillator based on a mo...
详细信息
Different from previous studies on memristive chaotic oscillators which tended to adopt common mathematical models but lacked practical consideration, in this paper, a novel memristive chaotic oscillator based on a modified voltage-controlled HP memristor model was proposed for the first time. By replacing Chua's diode with this model in a canonical Chua's circuit, we derived an oscillator characterized by rich dynamics such as special-shaped attractors, a wide range of chaos and insensitivity to the initial value of the memristor. These features were systematically investigated in terms of bifurcation diagrams, Poincaré map, time series, Lyapunov exponents, etc.
For speech emotion recognition, emotional feature set with high dimension may produce redundant features and influence the recognition accuracy. To solve this problem and obtain the optimal emotional feature subset of...
详细信息
For speech emotion recognition, emotional feature set with high dimension may produce redundant features and influence the recognition accuracy. To solve this problem and obtain the optimal emotional feature subset of speech, a feature dimension reduction based on linear discriminant analysis is proposed. According to the confusion degree between different basic emotions, an emotion recognition method based on support vector machine decision tree is proposed. Experiment on speaker-dependent speech emotion recognition using Chinese speech database from institute of automation of Chinese academy of sciences is performed and a speech emotion recognition system is presented, where standard feature sets of the INTER-SPEECH and classic classifiers are used in comparative experiments respectively. Experimental results show that the proposal achieves 84.39% recognition accuracy on average. By proposal, it would be fast and efficient to discriminate emotional states of diverse speakers from speech, and it would make it possible to realize the interaction between speaker and computer/robot in the future.
Aiming at the detection of moving objects in video series, a moving object detection algorithm based on background difference method and inter-frame difference method is proposed. A new background update method is pro...
详细信息
Aiming at the detection of moving objects in video series, a moving object detection algorithm based on background difference method and inter-frame difference method is proposed. A new background update method is proposed to update the unchanged background area into the background frame. Experiments show that this method overcomes the problems of false detection and empty in the previous detection algorithms. The method can meet the need of real-time detection and tracking of moving targets with the advantages of high accuracy and fast calculation speed.
暂无评论