Adaboost集成BP神经网络在传感器阵列检测系统中的应用

针对目前常见的多元有害气体检测问题,设计并搭建了一种基于传感器阵列和集成 BP神经网络相结合的传感器阵列检测系统。在该系统中采用集成BP神经网络对传感器阵列的三种混合有害气体的响应信号进行回归分析。为了提高集成BP神经网络的预测准确性,又利用Adaboost算法对集成BP神经网络进行了优化。结果显示：该系统能够准确地检测气体组分,通过Adaboost算法对集成BP神经网络优化后,预测的平均相对误差小于2%,能够有效解决气体传感器的交叉敏感问题,提高传感器的选择性。     

Effective recognition of MCCs in mammograms using an improved neural classifier

Computer-aided diagnosis is one of the most important engineering applications of artificial intelligence. In this paper, early detection of breast cancer through classification of microcalcification clusters from mammograms is emphasized. Although artificial neural network (ANN) has been widely applied in this area, the average accuracy achieved is only around 80% in terms of the area under the receiver operating characteristic curve A_z. This performance may become much worse when the training samples are imbalanced. As a result, an improved neural classifier is proposed, in which balanced learning with optimized decision making are introduced to enable effective learning from imbalanced samples. When the proposed learning strategy is applied to individual classifiers, the results on the DDSM database have demonstrated that the performance from has been significantly improved. An average improvement of more than 10% in the measurements of F₁ score and A_z has fully validated the effectiveness of our proposed method for the successful classification of clustered microcalcifications.     

A fully neural implementation of unitary response model for classification of gases/odors using the responses of thick film gas sensor array

In this paper, a classification scheme based on neurally implemented unitary response model (URM) for a gas/odor sensor array response has been presented. Thick-film tin-oxide sensor array responses for four gases/odors (viz. acetone, carbon tetra-chloride, ethyl methyl ketone and xylene) were first transformed into equivalent unitary responses. This transformation was carried out using a pre-trained neural ‘unitary response model pre-processor (URMP)’, called Net I_URMP. The classification of these responses in the unitary analysis space was then carried out, more accurately, using a pre-trained neural classifier called Net II_URMC. During this experiment, respective nets Net I_URMP and Net II_URMC, comprising of 12 and 8 neurons, were trained in just 23 and 09 epochs of 42 × 4 training response vectors. At stage I, the mean squared error (MSE) between neurally and mathematically obtained unitary response versions of 18 independent test responses for the considered gases/odors was 7.51 × 10⁻². At stage II, all the aforesaid test samples were correctly classified, with a MSE of 3.87 × 10⁻⁸. Further, by connecting Net I_URMP and Net II_URMC in cascade, the proposed classifier could be implemented using 16 neurons only.     

Nonlinear model identification and adaptive control of CO2 sequestration process in saline aquifers using artificial neural networks

In recent years, storage of carbon dioxide (CO₂) in saline aquifers has gained intensive research interest. The implementation, however, requires further research studies to ensure it is safe and secure operation. The primary objective is to secure the CO₂ which relies on a leak-proof formation. Reservoir pressure is a key aspect for assessment of the cap rock integrity. This work presents a new pressure control methodology based on a nonlinear model predictive control (NMPC) scheme to diminishing risk of carbon dioxide (CO₂) back leakage to the atmosphere due to a fail in the integrity of the formation cap rock. The CO₂ sequestration process in saline aquifers is simulated using ECLIPSE-100 as black oil reservoir simulator while the proposed control scheme is realized in MATLAB software package to prevent over-pressurization. A modified form of growing and pruning radial basis function (MGAP-RBF) neural network model is identified online for prediction of reservoir pressure behaviors. MGAP-RBF is recursively trained via extended Kalman filter (EKF) and unscented Kalman filter (UKF) algorithms. A set of miscellaneous test scenarios has been conducted using an interface program to exchange ECLIPSE and MATLAB in order to demonstrate the capabilities of the proposed methodology in guiding saline aquifer to follow some desired time-dependent pressure profiles during the CO₂ injection process.