Depression has become one of the most common psychological diseases, speech-based depression detection and severity recognition is a new trend in recent years. However, data insufficient issue and the significant imba...
详细信息
ISBN:
(纸本)9781538660577
Depression has become one of the most common psychological diseases, speech-based depression detection and severity recognition is a new trend in recent years. However, data insufficient issue and the significant imbalance among the different classes are the main challenge in the area at present. To solve the problem of sample insufficient and class imbalanced, this paper combines adaboost and collaborative representation (adaboost-CRC) to detect Severe Major Depression Disorders (SMDD). Firstly, Mel-Frequency Cepstral Coefficient (MFCCs) were extracted from the subject's speech;Then, aiming at the data imbalance issue, adaboost-CRC classifier structure was created in which adaboost was used to discriminate the result of each weak classifier according to its weight. The experimental framework of leave-one-speaker-out cross validation was adopted to assess the method's performance. The evaluation data comes from the Audio/Emotion Challenge and Workshop (AVEC) 2013 dataset. Experimental results show that the accuracy and sensitivity of adaboost-CRC are better than CRC's.
In order to solve the problems of correctly identifying fault classes in fault diagnosis of analogue circuit and improve classification ability, a fault diagnosis method for analog circuits based on adaboost algorithm...
详细信息
ISBN:
(纸本)9780769538655
In order to solve the problems of correctly identifying fault classes in fault diagnosis of analogue circuit and improve classification ability, a fault diagnosis method for analog circuits based on adaboost algorithm and Hyper-Sphere Support Vector Machine (Hyper-sphere SVM) is developed in this paper. This algorithm uses Hyper-sphere SVMs as weak learners of adaboost and use adaboost algorithm to improve the accuracy of weak learners. Simulation results of diagnosing an analog circuit show us the proposed technique has the higher classification accuracy compared with Support Vector Machine and has confirmed the validity of the method.
adaboost algorithm can achieve better performance by averaging over the predictions of some weak hypotheses. To improve the power of classification ability of adaboost, an infinite ensemble learning framework based on...
详细信息
ISBN:
(纸本)9783037850398
adaboost algorithm can achieve better performance by averaging over the predictions of some weak hypotheses. To improve the power of classification ability of adaboost, an infinite ensemble learning framework based on the Support Vector Machine was formulated. The framework can output an infinite adaboost through embedding infinite hypotheses into a new kernel of Support Vector Machine. The stump kernel embodies infinite decision stumps. At last, the algorithm was used in fault diagnosis for analog circuits. Experimental results show that infinite adaboost with Support Vector Machine is superior than finite adaboost with the same base hypothesis set. The purpose of enhancing classification accuracy of adaboost algorithm is achieved.
Least square support vector machine integrated with adaptive boost algorithm was applied to the transformer fault diagnosis. In order to obtain the training sample, characteristic gases dissolved in the faulty transfo...
详细信息
ISBN:
(纸本)9789811023385;9789811023378
Least square support vector machine integrated with adaptive boost algorithm was applied to the transformer fault diagnosis. In order to obtain the training sample, characteristic gases dissolved in the faulty transformer oil were collected and normalized, then a number of different classifiers are to be constructed though adaptive boost algorithm on the same training set. Subsequently, least squares support vector machine is used as the base classifier, which was fast in calculation and was improved by iteration in classification ability. The fault diagnosis results show that the method was simple and flexible, it has high accuracy rate of fault diagnosis. To a certain extent, this method makes up for the deficiencies of three-ratio method, such as code missing and boundary absolute.
The semiconductor production data is typically complex, nonlinear and high-dimension, and the traditional post-sampling quality inspection often have large errors and will bring the economic losses caused by defective...
详细信息
ISBN:
(纸本)9781538694145
The semiconductor production data is typically complex, nonlinear and high-dimension, and the traditional post-sampling quality inspection often have large errors and will bring the economic losses caused by defective products. Based on machine learning technologies, this research is aimed to establish the proper model to predict semiconductor quality in advance. Based on the requirements of actual production, the BP neural network and adaboost algorithm are combined, and a new BP-AdqBoost model is proposed after optimizing the adaboost algorithm. The data of LCD Monitor production was analyzed. Then the improved BP-AdqBoost model, BP neural network, and the unmodified BP-adaboost prediction results are compared by prediction accuracy and reliability. The comparison shows that the improved BP-AdqBoost model can not only improve the prediction accuracy, but also strengthen the prediction reliability, which would be useful to the practical semiconductor production.
Pedestrian detection is an important task in many applications such as intelligent transportation systems, image retrieval, surveillance systems, automated personal assistance, etc. This paper proposes a set of modifi...
详细信息
ISBN:
(纸本)9788993215045
Pedestrian detection is an important task in many applications such as intelligent transportation systems, image retrieval, surveillance systems, automated personal assistance, etc. This paper proposes a set of modified Haar-like features that have parallelogram shapes. Using the proposed feature descriptors to develop a rapid detection system for pedestrian detection based on decision tree structure used boosting algorithm. The experimental results showed that the proposed method could produce high accuracy detection rate with lower false positive rate and higher recall rate than original Haar-like features and it is efficiency with different resolutions and gestures under a variety of backgrounds as well as lighting.
In this paper, a novel combination method based on the adaboost algorithm and the general regression neural network (GRNN) is proposed to predict the depth-averaged current (DAC) for the next profile using the underwa...
详细信息
ISBN:
(纸本)9781728154466
In this paper, a novel combination method based on the adaboost algorithm and the general regression neural network (GRNN) is proposed to predict the depth-averaged current (DAC) for the next profile using the underwater gliders (UGs). Firstly, considering changes of the seawater density and the hull deformation, the velocity calculation model of UGs and the calculation method of DAC are given. Secondly, two DAC forecasting models are established with historical data using the support vector machine (SVM) and the back-propagation neural network (BPNN) methods, respectively. Then, the forecasting models are combined nonlinearly by adopting the GRNN. Finally, outputs from the GRNN are combined using the adaboost algorithm, which further taken for the DAC forecasting. A sea trial was conducted using Petrel-II glider in the South China Sea, which verified the accuracy of the three forecasting models. Results demonstrate that the proposed combination method has a better performance in DAC forecasting than the other two single forecasting models.
The background of this paper is the learners' expression recognition in E-learning. In the paper, the method of the face detection based on the adaboost algorithm and a set of haar wavelet like features. To improv...
详细信息
ISBN:
(纸本)9781467347143
The background of this paper is the learners' expression recognition in E-learning. In the paper, the method of the face detection based on the adaboost algorithm and a set of haar wavelet like features. To improve the performance of the detectors, the face-contour is combined with the adaboost. The experimental results demonstrate that it can find the position of the detected faces of learners in E-learning accurately.
With the aid of AI-based methods like convolution neural networks, this article seeks to enhance weed detection and removal. A plant that is not wanted and is growing wild, especially one that does so on cultivated la...
详细信息
In order to achieve a stable operation and optimized scheduling of new energy power systems, this study proposes a multi-temporal and spatial scale accurate prediction method for new energy power based on the BP Adabo...
详细信息
暂无评论