2771-1463ISSN (Online)
2771-1471ISSN (Print)
Remote Sensing Scene Classification (RSSC) is the distinctive classification of remote sensing images into numerous classes of scene classifications based on the image content. RSSC plays a significant role in several domains, like land mapping, agriculture, and the classification of disaster-prone regions. The Internet of Things (IoT) is a dynamic global network of devices, for example, vehicles, sensors, actuators, surveillance cameras, etc. These interconnected objects were distinctively recognizable and they could separately transfer and obtain valuable data through the network. However, satellite images were frequently degraded and blurred owing to aerosol dispersion under haze, fog, and other weather circumstances, decreasing the color fidelity and contrast of the image. To use effectual RSSC in real-time, widespread researchers concentrate on creating aerospace image processing systems, like airborne or spaceborne systems. Recently, with the quick improvement of deep learning (DL) and Machine learning (ML) techniques, the performance of RSSC has significantly developed owing to the hierarchical feature representation learning. Both technique has greater achievement in the domain of image scene classification. This study presents a Leveraging Tiny Convolutional Neural Networks with a Water Cycle Algorithm for Remote Sensing Scene Classification (LTCNN-WCRSSC) model. The LTCNN-WCRSSC technique is designed for efficient RSS classification in resource-constrained devices with on-board training capabilities. At first, the LTCNN-WCRSSC model applies image processing using a median filter (MF) to eliminate the noise. Next, the feature extraction process can be exploited by the ConvNeXt-Tiny method. For the RSSC model, the spatiotemporal attention bidirectional long short-term memory (STA-BiLSTM) technique is performed. Eventually, the water cycle algorithm (WCA)-based hyperparameter choice process can be performed to optimize the classification results of the STA-BiLSTM algorithm. The experimental evaluation of the LTCNN-WCRSSC technique takes place using a benchmark image dataset. The stimulated results indicated the superior performances of the LTCNN-WCRSSC model over other approaches.
Read MoreDoi: https://doi.org/10.54216/JCHCI.090101
Vol. 9 Issue. 1 PP. 01-19, (2025)
In Cognitive Radio Networks (CRNs), Peak-to-Average-Power-Ratio (PAPR) reduction is crucial for mitigating distortion in signals while optimizing spectral efficiency. This work offers a novel strategy for effectively reducing that PAPR in CRN systems, especially when secondary users are incorporated, by utilizing VLSI (Very-Large-Scale Integration) design approaches. The proposed strategy investigates VLSI methods for PAPR reduction, such as Partial-Transmit-Sequence (PTS) techniques. The system is appropriate for CRN applications because it can accomplish real-time PAPR reduction while preserving low power consumption and compact size by implementing these approaches in VLSI hardware. This could entail particular strategies for controlling PAPR with secondary users, such as joint PAPR and spectrum sensing approaches, dynamic power allocation, or user scheduling algorithms. Utilizing the predetermined values of pilot tones, the suggested decoder investigates every possible combination of weighting variables to determine which combination the transmitter has chosen and employed. There appears to be no data rate loss with the proposed decoder since it doesn't require any more pilot tones. This study next gives a digital execution of the described PTS decoder and illustrates its low power qualities, as well as the design and The encoder required at the transmitter to operate the suggested system is being developed using VLSI. The suggested architecture makes it easier for SUs to integrate with CRNs seamlessly. It allows SUs to effectively take advantage of available spectrum opportunities while complying with CRN restrictions and reducing interference with primary users by tackling PAPR and spectrum sensing concurrently. Furthermore, the study discusses the difficulties of incorporating secondary users into CRNs while retaining PAPR management.
Read MoreDoi: https://doi.org/10.54216/JCHCI.090102
Vol. 9 Issue. 1 PP. 20-30, (2025)
Intracranial hemorrhage (ICH) poses a large chance to affected person fitness, regularly modern requiring set off diagnosis and intervention. In latest years, the medical imaging techniques, specifically computed tomography (CT) scanning, have end up critical tools for detecting and characterizing ICH. This paper offers a complete evaluate comprehensive review of the state-of-the-art techniques for the segmentation, category, and visualization cutting-edge intracranial hemorrhage in CT mind pics. The evaluate encompasses numerous methodologies, consisting of conventional picture processing strategies, system cutting-edge algorithms, and deep brand new strategies, highlighting their strengths, limitations, and capability applications in scientific exercise. Additionally, it discusses the challenges associated with correct ICH detection and quantification, inclusive of the presence modern day artifacts, anatomical variations, and sophistication imbalance. Furthermore, the paper explores emerging tendencies in ICH research, which includes the combination trendy multimodal imaging information and the improvement trendy interactive visualization gear for enhanced medical choice-making. The segmented portion from each CT image is constructed into a single 3D volumetric structure and essential information such as region Area, volume and location are provided. Further the classification accuracy between normal brain and ICH brain is 95.8%. Such a 3D visualization, Classification and volumetric analysis of ICH can provide the exact and necessary information to the neurologist which is essential for the treatment of ICH.
Read MoreDoi: https://doi.org/10.54216/JCHCI.090103
Vol. 9 Issue. 1 PP. 31-44, (2025)