Proposed Framework for Semantic Segmentation of Aerial Hyperspectral Images Using Deep Learning and SVM Approach

المجلة: Fusion: Practice and Applications.

سنة النشر: 2024

تاريخ النشر: 2024-02-02

The combination of deep neural networks and assistance vector machines for hyperspectral image recognition is presented in this work. A key issue in the real-world hyperspectral imaging system is hyperspectral picture recognition. Although deep learning can replicate highly dimensional feature vectors from source data, it comes at a high cost in terms of time and the Hugh phenomenon. The selection of the kernel feature and limit has a significant impact on the presentation of a kernel-based learning system. We introduce Support Vector Machine (SVM), a kernel learning method that is used to feature vectors obtained from deep learning on hyperspectral images. By modifying the data structure's parameters and kernel functions, the learning system's ability to solve challenging problems is enhanced. The suggested approaches' viability is confirmed by the outcomes of the experiments. At a particular rate, accuracy of testing for classification is around 90%. Moreover, to significantly make framework robust, validation is done using 5-flod verification. Keywords: Computer science; hyperspectral images; kernel; deep learning

A novel data offloading scheme for QoS optimization in 5G based internet of medical things

المجلة: Bulletin of Electrical Engineering and Informatics

سنة النشر: 2023

تاريخ النشر: 2023-11-01

The internet of medical things (IoMT), which is expected the lead to the biggest technology in worldwide distribution. Using 5th generation (5G) transmission, market possibilities and hazards related to IoMT are improved and detected. This framework describes a strategy for proactively addressing worries and offering a forum to promote development, alter attitudes and maintain people's confidence in the broader healthcare system without compromising security. It is combined with a data offloading system to speed up the transmission of medical data and improved the quality of service (QoS). As a result of this development, we suggested the enriched energy efficient fuzzy (EEEF) data offloading technique to enhance the delivery of data transmission at the original targeted location. Initially, healthcare data was collected. Preprocessing is achieved by the normalization method. An EEEF data offloading scheme is proposed. A fruit fly optimization (FFO) technique is utilized. The performance metrics such as energy consumption, delay, resource utilization, scalability, and packet loss are analyzed and compared with existing techniques. The future scope will make use of a revolutionary optimization approach for IoMT.