Forecasting the western Pacific subtropical high index during typhoon activity using a hybrid deep learning model

Seasonal location and intensity changes in the western Pacific subtropical high(WPSH)are important factors dominating the synoptic weather and the distribution and magnitude of precipitation in the rain belt over East Asia.Therefore,this article delves into the forecast of the western Pacific subtropical high index during typhoon activity by adopting a hybrid deep learning model.Firstly,the predictors,which are the inputs of the model,are analysed based on three characteristics:the first is the statistical discipline of the WPSH index anomalies corresponding to the three types of typhoon paths;the second is the correspondence of distributions between sea surface temperature,850 hPa zonal wind(u),meridional wind(v),and 500 hPa potential height field;and the third is the numerical sensitivity experiment,which reflects the evident impact of variations in the physical field around the typhoon to the WPSH index.Secondly,the model is repeatedly trained through the backward propagation algorithm to predict the WPSH index using 2011–2018 atmospheric variables as the input of the training set.The model predicts the WPSH index after 6 h,24 h,48 h,and 72 h.The validation set using independent data in 2019 is utilized to illustrate the performance.Finally,the model is improved by changing the CNN2D module to the DeCNN module to enhance its ability to predict images.Taking the 2019 typhoon“Lekima”as an example,it shows the promising performance of this model to predict the 500 hPa potential height field.

A Novel Hybrid Architecture for Superior IoT Threat Detection through Real IoT Environments

As the Internet of Things(IoT)continues to expand,incorporating a vast array of devices into a digital ecosystem also increases the risk of cyber threats,necessitating robust defense mechanisms.This paper presents an innovative hybrid deep learning architecture that excels at detecting IoT threats in real-world settings.Our proposed model combines Convolutional Neural Networks(CNN),Bidirectional Long Short-Term Memory(BLSTM),Gated Recurrent Units(GRU),and Attention mechanisms into a cohesive framework.This integrated structure aims to enhance the detection and classification of complex cyber threats while accommodating the operational constraints of diverse IoT systems.We evaluated our model using the RT-IoT2022 dataset,which includes various devices,standard operations,and simulated attacks.Our research’s significance lies in the comprehensive evaluation metrics,including Cohen Kappa and Matthews Correlation Coefficient(MCC),which underscore the model’s reliability and predictive quality.Our model surpassed traditional machine learning algorithms and the state-of-the-art,achieving over 99.6%precision,recall,F1-score,False Positive Rate(FPR),Detection Time,and accuracy,effectively identifying specific threats such as Message Queuing Telemetry Transport(MQTT)Publish,Denial of Service Synchronize network packet crafting tool(DOS SYN Hping),and Network Mapper Operating System Detection(NMAP OS DETECTION).The experimental analysis reveals a significant improvement over existing detection systems,significantly enhancing IoT security paradigms.Through our experimental analysis,we have demonstrated a remarkable enhancement in comparison to existing detection systems,which significantly strength-ens the security standards of IoT.Our model effectively addresses the need for advanced,dependable,and adaptable security solutions,serving as a symbol of the power of deep learning in strengthening IoT ecosystems amidst the constantly evolving cyber threat landscape.This achievement marks a significant stride towards protecting the integrity of IoT infrastructure,ensuring operational resilience,and building privacy in this groundbreaking technology.

Smart Object Detection and Home Appliances Control System in Smart Cities

During the last decade the emergence of Internet of Things(IoT)based applications inspired the world by providing state of the art solutions to many common problems.From traffic management systems to urban cities planning and development,IoT based home monitoring systems,and many other smart applications.Regardless of these facilities,most of these IoT based solutions are data driven and results in small accuracy values for smaller datasets.In order to address this problem,this paper presents deep learning based hybrid approach for the development of an IoT-based intelligent home security and appliance control system in the smart cities.This hybrid model consists of;convolution neural network and binary long short term model for the object detection to ensure safety of the homes while IoT based hardware components like;Raspberry Pi,Amazon Web services cloud,and GSM modems for remotely accessing and controlling of the home appliances.An android application is developed and deployed on Amazon Web Services(AWS)cloud for the remote monitoring of home appliances.A GSM device and Message queuing telemetry transport(MQTT)are integrated for communicating with the connected IoT devices to ensure the online and offline communication.For object detection purposes a camera is connected to Raspberry Pi using the proposed hybrid neural network model.The applicability of the proposed model is tested by calculating results for the object at varying distance from the camera and for different intensity levels of the light.Besides many applications the proposed model promises for providing optimum results for the small amount of data and results in high recognition rates of 95.34%compared to the conventional recognition model(k nearest neighbours)recognition rate of 76%.

Surveillance-image-based outdoor air quality monitoring

Air pollution threatens human health,necessitating effective and convenient air quality monitoring.Recently,there has been a growing interest in using camera images for air quality estimation.However,a major challenge has been nighttime detection due to the limited visibility of nighttime images.Here we present a hybrid deep learning model,capitalizing on the temporal continuity of air quality changes for estimating outdoor air quality from surveillance images.Our model,which integrates a convolutional neural network(CNN)and long short-term memory(LSTM),adeptly captures spatial-temporal image features,enabling air quality estimation at any time of day,including PM_(2.5) and PM10 concentrations,as well as the air quality index(AQI).Compared to independent CNN networks that solely extract spatial features,our model demonstrates superior accuracy on self-constructed datasets with R^(2)?0.94 and RMSE=5.11 mg m^(-3) for PM_(2.5),R^(2)=0.92 and RMSE=7.30 mg m^(-3) for PM10,and R^(2)=0.94 and RMSE?5.38 for AQI.Furthermore,our model excels in daytime air quality estimation and enhances nighttime predictions,elevating overall accuracy.Validation across diverse image datasets and comparative analyses underscore the applicability and superiority of our model,reaffirming its applicability and superiority for air quality monitoring.