Weather Forecasting App is a based-on web application that provide the exact the weather data of user's location. In the proposed web application, there are many parameters used like humidity, wind pressure, wind ...
详细信息
Machine learning has been adopted for efficient cooperative spectrum sensing. However, it incurs an additional security risk due to attacks leveraging adversarial machine learning to create malicious spectrum sensing ...
详细信息
ISBN:
(数字)9798350383508
ISBN:
(纸本)9798350383515
Machine learning has been adopted for efficient cooperative spectrum sensing. However, it incurs an additional security risk due to attacks leveraging adversarial machine learning to create malicious spectrum sensing values to deceive the fusion center, called adversarial spectrum attacks. In this paper, we propose an efficient framework for detecting adversarial spectrum attacks. Our design leverages the concept of the distance to the decision boundary (DDB) observed at the fusion center and compares the training and testing DDB distributions to identify adversarial spectrum attacks. We create a computationally efficient way to compute the DDB for machine learning based spectrum sensing systems. Experimental results based on realistic spectrum data show that our method, under typical settings, achieves a high detection rate of up to 99% and maintains a low false alarm rate of less than 1%. In addition, our method to compute the DDB based on spectrum data achieves 54%–64% improvements in computational efficiency over existing distance calculation methods. The proposed DDB-based detection framework offers a practical and efficient solution for identifying malicious sensing values created by adversarial spectrum attacks.
In recent years,federated learning(FL)has played an important role in private data-sensitive scenarios to perform learning tasks collectively without data ***,due to the centralized model aggregation for heterogeneous...
详细信息
In recent years,federated learning(FL)has played an important role in private data-sensitive scenarios to perform learning tasks collectively without data ***,due to the centralized model aggregation for heterogeneous devices in FL,the last updated model after local training delays the convergence,which increases the economic cost and dampens clients’motivations for participating in *** addition,with the rapid development and application of intelligent reflecting surface(IRS)in the next-generation wireless communication,IRS has proven to be one effective way to enhance the communication *** this paper,we propose a framework of federated learning with IRS for grouped heterogeneous training(FLIGHT)to reduce the latency caused by the heterogeneous communication and computation of the ***,we formulate a cost function and a greedy-based grouping strategy,which divides the clients into several groups to accelerate the convergence of the FL *** simulation results verify the effectiveness of FLIGHT for accelerating the convergence of FL with heterogeneous *** the exemplified linear regression(LR)model and convolutional neural network(CNN),FLIGHT is also applicable to other learning models.
Wind energy is featured by instability due to a number of factors,such as weather,season,time of the day,climatic area and so ***,instability in the generation of wind energy brings new challenges to electric power gr...
详细信息
Wind energy is featured by instability due to a number of factors,such as weather,season,time of the day,climatic area and so ***,instability in the generation of wind energy brings new challenges to electric power grids,such as reliability,flexibility,and power *** transition requires a plethora of advanced techniques for accurate forecasting of wind *** this context,wind energy forecasting is closely tied to machine learning(ML)and deep learning(DL)as emerging technologies to create an intelligent energy management *** article attempts to address the short-term wind energy forecasting problem in Estonia using a historical wind energy generation data ***,we taxonomically delve into the state-of-the-art ML and DL algorithms for wind energy forecasting and implement different trending ML and DL algorithms for the day-ahead *** the selection of model parameters,a detailed exploratory data analysis is *** models are trained on a real-time Estonian wind energy generation dataset for the first time with a frequency of 1 *** main objective of the study is to foster an efficient forecasting technique for *** comparative analysis of the results indicates that Support Vector Machine(SVM),Non-linear Autoregressive Neural Networks(NAR),and Recurrent Neural Network-Long-Term Short-Term Memory(RNNLSTM)are respectively 10%,25%,and 32%more efficient compared to TSO’s forecasting ***,RNN-LSTM is the best-suited and computationally effective DL method for wind energy forecasting in Estonia and will serve as a futuristic solution.
IEEE802.11,known as WiFi has proliferated in the last *** can be found in smartphones,laptops,smart TVs and surveillance *** popularity has revealed many issues in health,data privacy and *** this work,a WiFi measurem...
详细信息
IEEE802.11,known as WiFi has proliferated in the last *** can be found in smartphones,laptops,smart TVs and surveillance *** popularity has revealed many issues in health,data privacy and *** this work,a WiFi measurement study has been conducted in Amman,the capital city of *** Android App has been written to harvest WiFi information of the transmitted frames of any surrounding Access points(APs).More than 240,000 APs information has been harvested in this *** harvested data have been analyzed to find statistics ofWiFi devices in this ***,three power distribution models have been derived from the data for three different areas,closed,open and hybrid *** addition,the collected data revealed that the SSID can be leveraged as a landmark for the access points(APs).To this end,SSIDtrack algorithm is proposed to track shoppers/walkers in closed areas,such as malls to find their walking route utilizing only the SSID information collected from the surrounding *** algorithm has been tested in two different malls that consist of four different *** accuracy recorded for the algorithm acceded 95%.
Stock price forecasting is one of the most researched topics because it appeals to both the academic and commercial communities. Since the development of artificial intelligence, a great number of different algorithms...
详细信息
Control systems achieve the desired performance with the model-based controller if the dynamical model of the actual plant is given with sufficient accuracy. However, if there exists a difference between the actual pl...
详细信息
Fish diseases are among the major limiting factors to increase global aquaculture production. They lead to increased fish mortality, low breeding and growth rates, and low meat quality. The success of aquaculture is h...
详细信息
Peer-to-peer learning is an increasingly popular framework that enables beyond-5G distributed edge devices to collaboratively train deep neural networks in a privacy-preserving manner without the aid of a central serv...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
Peer-to-peer learning is an increasingly popular framework that enables beyond-5G distributed edge devices to collaboratively train deep neural networks in a privacy-preserving manner without the aid of a central server. Neural network training algorithms for emerging environments, e.g., smart cities, have many design considerations that are difficult to tune in deployment settings – such as neural network architectures and hyperparameters. This presents a critical need for characterizing the training dynamics of distributed optimization algorithms used to train highly nonconvex neural networks in peer-to-peer learning environments. In this work, we provide an explicit characterization of the learning dynamics of wide neural networks trained using popular distributed gradient descent (DGD) algorithms. Our results leverage both recent advancements in neural tangent kernel (NTK) theory and extensive previous work on distributed learning and consensus. We validate our analytical results by accurately predicting the parameter and error dynamics of wide neural networks trained for classification tasks.
暂无评论