Electroencephalogram (EEG) data-based emotion recognition has acquired popularity in recent years. Because EEG signals are noisy, non-linear, and non-stationary, it is challenging to develop an intelligent framework c...
详细信息
Natural disasters such as earthquakes, floods, Thunderstorms, cyclones, and rainfall pose significant risks to human life and infrastructure. Traditional prediction methods often rely on physical sensors, meteorologic...
详细信息
Natural disasters such as earthquakes, floods, Thunderstorms, cyclones, and rainfall pose significant risks to human life and infrastructure. Traditional prediction methods often rely on physical sensors, meteorological data, and historical patterns, which may not always provide timely or accurate warnings. To investigate the feasibility of using sentiment analysis on GIS-based data in social media posts like Twitter, Facebook, Google News and other textual data to predict natural disasters in tropical regions. By analyzing the sentiment of communications related to weather conditions, emergency alerts, and public reactions, the study seeks to identify patterns and correlations that may serve as early indicators of impending disasters. The ultimate goal is to enhance early warning systems and improve disaster preparedness by integrating sentiment analysis with traditional prediction models. Sentiment keyword graph filtering Technique (SKG) is used to remove neural text keyword-based filtering for disaster-related terms and graph-based filtering for central node. A deep neural network (DNN) is used to classify and analyze sentiment from social media posts. adam optimization algorithm (AOA) is used to optimise model parameters to minimize the loss function, improving prediction accuracy. The evaluation is conducted on Matlab or Python based on parameters such as adam accelerates convergence, reducing training time and computational resources and for natural disaster prediction are disaster occurrence risk factors, disaster probability, event timelines, geospatial alerts, early warning alerts, and confidence intervals. The result shows that the Proposed Model demonstrates superior performance with consistently high accuracy rates, peaking at 98.8, implemented using Python software. The future scope of this research is vast and promising, with potential expansions including integration with IoT devices, multilingual support, real-time processing, and more, to enhance th
Nowadays, smart health technologies are used in different life and environmental areas, such as smart life, healthcare, cognitive smart cities, and social systems. Intelligent, reliable, and ubiquitous healthcare syst...
详细信息
Nowadays, smart health technologies are used in different life and environmental areas, such as smart life, healthcare, cognitive smart cities, and social systems. Intelligent, reliable, and ubiquitous healthcare systems are a part of the modern developing technology that should be more seriously considered. Data collection through different ways, such as the Internet of things (IoT)-assisted sensors, enables physicians to predict, prevent and treat diseases. Machine Learning (ML) algorithms may lead to higher accuracy in medical diagnosis/prognosis based on health data provided by the sensors to help physicians in tracking symptom significance and treatment steps. In this study, we applied four ML methods to the data on Parkinson's disease to assess the methods' performance and identify the essential features that may be used to predict the total Unified Parkinson's disease Rating Scale (UPDRS). Since accessibility and high-performance decision-making are so vital for updating physicians and supporting IoT nodes (e.g., wearable sensors), all the data is stored, updated as rule-based, and protected in the cloud. Moreover, by assigning more computational equipment and memory in use, cloud computing makes it possible to reduce the time complexity of the training phase of ML algorithms in the cases we want to create a complete structure of cloud/edge architecture. In this situation, it is possible to investigate the approaches with varying iterations without concern for system configuration, temporal complexity, and real-time performance. Analyzing the coefficient of determination and Mean Square Error (MSE) reveals that the outcomes of the applied methods are mostly at an acceptable performance level. Moreover, the algorithm's estimated weight indicates that Motor UPDRS is the most significant predictor of Total UPDRS.
High-precision temperature control technology is currently more and more important in industrial thermal processing systems. In this paper, an RNN controller with integral-proportional-derivative (IPD) compensation dr...
详细信息
High-precision temperature control technology is currently more and more important in industrial thermal processing systems. In this paper, an RNN controller with integral-proportional-derivative (IPD) compensation driven by a reference model is proposed for single phase hotplate temperature control systems. A reference model is introduced based on the real controlled plant for the RNN controller to obtain better self-learning and adjusting efficiency by providing a more valuable teaching signal. Further, an adam optimization algorithm is applied to improve the control performance of the RNN controller. The simulations were developed under a MATLAB environment and the experiments were performed on a temperature experimental platform that used a digital-signal-processor (DSP) as digital controller. The results of simulations and experiments were quantitatively compared with those for a conventional temperature control system which only had an IPD controller. The control efficiency of the proposed RNN method was successfully evaluated.
Data classification effectively classifies the data based on the labeled class distribution. To classify the data using the imbalanced distribution poses a significant challenge in the class inequity problem. Various ...
详细信息
Data classification effectively classifies the data based on the labeled class distribution. To classify the data using the imbalanced distribution poses a significant challenge in the class inequity problem. Various data classification methods are developed in the learning framework, but proving better classification accuracy is a significant challenge in the application domain. Therefore, an effective classification method named adam-Cuckoo search based Deep Belief Network (adam-CS based DBN) is proposed to perform the classification process. At first, the input data is forwarded to the pre-processing stage, and then the feature selection stage. The wrapper-based feature selection model conducts the search in space with the possible parameters. The operators specify the connectivity between the states and select the features based on their state. The classification is performed using the Deep Belief Network (DBN) classifier such that the multilayer perceptron (MLP) layer of Deep Belief Network (DBN) is trained using the proposed adam based Cuckoo search (adam-CS) algorithm. The breeding behavior of cuckoos is integrated with the step size parameter to enhance the accuracy of the classification process. The adaptive learning rate parameter effectively estimates the moments using a sparse gradient. The proposed adam based Cuckoo search (adam-CS) algorithm attained better performance using the metrics, such as accuracy, specificity, and sensitivity, with 90% training data.
Deep Neural Networks (DNNs) are vulnerable to adversarial examples that mislead DNNs with imperceptible perturbations. Existing adversarial attacks often exhibit weak transferability under the black-box setting, espec...
详细信息
ISBN:
(纸本)9783031159190;9783031159183
Deep Neural Networks (DNNs) are vulnerable to adversarial examples that mislead DNNs with imperceptible perturbations. Existing adversarial attacks often exhibit weak transferability under the black-box setting, especially when attacking the models with defense mechanisms. In this work, we regard the adversarial example generation problem as the problem of optimizing DNNs, and propose Nesterov adam Iterative Fast Gradient Method (NAI-FGM) which applies Nesterov accelerated gradient and adam to iterative attacks to improve the transferability of the gradient-based attack method so as to adjust the attack step size by itself and avoid local optimum more effectively. Empirical results on ImageNet dataset demonstrate that NAI-FGM could improve transferability of adversarial examples. Under the setting of ensemble model, the integrated method of NAI-FGM with various input transformations could achieve an average attack success rate of 91.88% against six advanced defense models, 1.78%-3.3% higher than the benchmarks. Code is available at https://***/NinelM/NAI-FGM.
In allusion to the problem of friction,leakage,vibration and noise existing in continuous rotary motor electro-hydraulic servo system,highly nonlinearity and uncertainties affecting the system performance,based on the...
详细信息
In allusion to the problem of friction,leakage,vibration and noise existing in continuous rotary motor electro-hydraulic servo system,highly nonlinearity and uncertainties affecting the system performance,based on the transfer function of electro-hydraulic servo system,a kind of Pol-Ind friction model is *** parameters of Pol-Ind friction model are identified and the accurate mathematical model of friction torque is obtained by *** self-correcting wavelet neural network(WNN)controller is proposed,and adam optimization algorithm is used to perform gradient optimization on scale factor and displacement factor in wavelet basis function,so as to improve the speed and precision of parameter *** comparative simulation analysis,it is clearly that the self-correcting WNN controller can effectively improve the frequency response and tracking accuracy of continuous rotary motor electro-hydraulic servo system.
A Recurrent Neural Network (RNN) is a special neural network sequence model that is very suitable for dealing with time series tasks. In various industrial processing systems, it has achieved good performances. In thi...
详细信息
ISBN:
(纸本)9781728162072
A Recurrent Neural Network (RNN) is a special neural network sequence model that is very suitable for dealing with time series tasks. In various industrial processing systems, it has achieved good performances. In this paper, a RNN model which is driven by an ideal reference model is proposed for the single-input single-output(SISO) temperature control system with time-delay. An ideal reference model is introduced to provides a more valuable teaching signal for helping RNN controller to obtain higher learning efficiency and providing suitable control input to the temperature control system. Meanwhile, adam optimization algorithm which can get adaptive learning rates is used to update parameters and improve the control performance of the RNN. Further, a classical integral proportional derivative (I-PD) controller is designed to reduce the effects caused by the temperature setting value kick during the RNN learning period. Simulations were developed under the MATLAB environment to evaluate the proposed control system performance. In order to demonstrate the efficiency and application of the proposed RNN control method, the simulation results based on the actual temperature model are compared quantitatively.
Opinion mining and sentiment analysis are useful to extract subjective information out of bulk text documents. Predicting the customer's opinion on amazon products has several benefits like reducing customer churn...
详细信息
Opinion mining and sentiment analysis are useful to extract subjective information out of bulk text documents. Predicting the customer's opinion on amazon products has several benefits like reducing customer churn, agent monitoring, handling multiple customers, tracking overall customer satisfaction, quick escalations, and upselling opportunities. Though performing sentiment analysis is a challenging task for the researchers to identify the user's sentiments from the large datasets, it is unstructured in nature, and also includes slangs, misspells, and abbreviations. To address this problem, a new proposed system is developed in this research study. Here, the proposed system comprises of four major phases;they are data collection, pre-processing, keyword extraction, and classification. Initially, the input data were collected from the dataset: amazon customer review. After collecting the data, pre-processing was carried out for enhancing the quality of collected data. The pre-processing phase comprises of three systems: lemmatization, review spam detection, and removal of stop words and URLs. Then, an effective topic modelling approach latent Dirichlet allocation along with modified possibilistic fuzzy C-Means was applied to extract the keywords and also helps in identifying the concerned topics. The extracted keywords were classified into three forms (positive, negative, and neutral) by applying an effective machine learning classifier: Selective memory architecture-based convolutional neural network. The experimental outcome showed that the proposed system enhanced the accuracy in sentiment analysis up to 6-20% related to the existing systems.
作者:
Jia, YanqinBeijing Inst Technol
Key Lab Photo Elect Imaging Technol & Syst Minist Educ China Beijing 100081 Peoples R China
Super-resolution reconstructed convolution neural network (SRCNN) is widely used in image quality improvement of single image. Traditional SRCNN training uses the loss function of minimum mean square error (MSE) and t...
详细信息
ISBN:
(纸本)9781510636552
Super-resolution reconstructed convolution neural network (SRCNN) is widely used in image quality improvement of single image. Traditional SRCNN training uses the loss function of minimum mean square error (MSE) and the method based on stochastic gradient descent (SGD) to optimize. Its learning rate adjustment strategy is limited by pre-specified adjustment rules, and it is difficult to select the initial value. Considering the complex texture and low resolution of remote sensing images, a deconvolution layer is proposed to replace the bi-cubic interpolation enlarged image in the traditional SRCNN network to overcome the mosaic effect. At the same time, adam optimizer is used to control the network training. After considering the first and second moment estimation of gradient comprehensively, the update step is calculated. Thus, the adaptive update of learning rate is realized and the speed of network training is greatly accelerated. The simulation results show that this method has advantages in edge reconstruction and texture details compared with the conventional superresolution reconstruction algorithm.
暂无评论