The paper analyses and studies the classification and characteristics of Internet of Things (IoT) information, and discusses the construction and application of Hadoop Cloud Platform. This paper mainly carries out from two aspects. One is to design the system architecture of the Open Platform for Data Simulation Resources of the IoT and design the key modules. A platform for data simulation resources of the IoT is built to provide the running environment and external services for the sensor data simulation model established. On the other hand, it is the key method to study the simulation data model based on IoT sensors. That is, based on the research environment of the IoT built by the existing laboratories, collect the data of sensors, analyze and study the characteristics of sensors in the IoT, and design the key algorithms for data simulation. This paper presents two key models for sensor data modeling: the Long Short-term Memory (LSTM) prediction model and the Support Vector Machine (SVM) model based on IoT data, which are suitable for different data volumes. Extensive simulations are executed to validate the remarkable nature in Hadoop platform, in terms of prediction accuracy and training efficiency under different working condition. INDEX TERMS Energy analysis, Internet of Things, cloud platform, Hadoop.
With the change of the network communication environment in vehicular ad hoc networks (VANETs) of a smart city, vehicles may encounter security threats such as eavesdropping, positioning, and tracking, so appropriate anonymity protection is required. Based on the certificateless cryptosystem and group signature ideas, this paper proposes a certificateless group signature anonymous authentication scheme for the VANETs of a smart city. In this scheme, it can implement the process of adding, signing, verifying, and revoking group members only by simple multiplication of the elliptic curve and synchronization factor technology, which shortens the length of the signature and improves the efficiency of the signature. From the proofs of correctness and security, we know that it does not only has anonymity and traceability of the group signature scheme but also has unforgeability and forward security. According to the performance verification, this scheme has lower calculation overhead and higher authentication efficiency.
Smoke is translucent and irregular, resulting in a very complex mix between background and smoke. Thin or small smoke is visually inconspicuous, and its boundary is often blurred. Therefore, it is a very difficult task to completely segment smoke from images. To solve the above issues, a multi-scale semantic segmentation for fire smoke based on global information and U-Net is proposed. This algorithm uses multi-scale residual group attention (MRGA) combined with U-Net to extract multi-scale smoke features, and enhance the perception of small-scale smoke. The encoder Transformer was used to extract global information, and improve accuracy for thin smoke at the edge of images. Finally, the proposed algorithm was tested on smoke dataset, and achieves 91.83% mIoU. Compared with existing segmentation algorithms, mIoU is improved by 2.87%, and mPA is improved by 3.42%. Thus, it is a segmentation algorithm for fire smoke with higher accuracy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.