Using cloud computing, businesses can adopt IT without incurring a significant upfront cost. The Internet has numerous benefits, but model security remains a concern, which affects cloud embracing negatively. The security challenge gets too difficult underneath data center, while additional dimensions such as model design, multitenancy, elasticity, and the layers dependency stack have been added to the problem scope. We present a thorough examination of the cloud security challenge in this article. We looked at the issue from the standpoints of network infrastructure: cloud-provided features, cloud consumers, and cloud service delivery methods. Based on this research, we developed an in-depth characterization of the data protection challenge and recommended security solutions that should address the critical aspects of the issue. Cloud computing is an exploding field of research that relies on distributing computing power instead of using dedicated computers or smart devices. Most of the growth in this sector is attributed to the indispensability of electronic and digital gadgets and the shift from a traditional IT subscription model to a unique cloud model. Cloud computing offered a significant danger and difficulty for information system projects, but it also provided them with several possibilities to improve their data processing. It has also been noted that cloud users and consumers do not yet have the necessary forensic skills to detect illegal activity in the cloud. Although the cloud offers potential technological and economic advantages, consumers have been reluctant to adopt it primarily due to security concerns and the difficulty of conducting an appropriate investigation into the cloud. Some study has been done in this area, and strategies for conducting forensic investigations have been proposed. In this research paper, we begin by analyzing the intrusion detection progress made by other academics, and then we analyze and evaluate our conclusions in order to assess the potential difficulties that cloud forensics face based on these findings.

Deep learning has recently been hailed as the most advanced computer vision technology for image classification. The invention of convolutional neural network (CNN) simplified the effort of feature engineering. Classification of various stages of fruit maturity using machine learning algorithms is a difficult task since it is difficult to distinguish the visual features of the fruits at different maturity stages. Fruit ripeness is critical in agriculture since it impacts the quality of the fruit. Manually determining the maturity of the fruit has various flaws, including the fact that it takes a long time, needs a lot of labor, and can lead to inconsistencies. In developing countries, agriculture is one of the most important economic sectors. Created system can be employed in the food processing business, in real-life applications where the intelligent system’s accuracy, cost, and speed will improve the production rate and allow satisfying consumer demand. With small number of image samples, the system is capable of automating assembly line related work for classifying bananas along with sufficient overall accuracy. The noninvasive method will also be used to classify other clustered fruits or horticultural crops in the future. The system can either replace or aid human operators who can focus their efforts on fruit selection. The combined merits of RGB and HSI (hyperspectral imaging) for classification of bananas were highlighted in the present study; they have possible application as a model for classification of several types of horticultural produce. The multi-input model’s quick processing time can be a useful and handy technique in the farm field during postharvest procedures. Via a combination of CNN and MLP applied to data collected using RGB and hyperspectral imaging, the multi-input model reliably recognizes bananas with an accuracy level of 98.4 percent as well as an F1-score of 0.97. The AI algorithm predicted the size (large, medium, and microscopic) and perspective (front or rear half) of banana classes with 99 percent accuracy. In comparison to previous studies that simply employed RGB imaging, the presented model revealed the value of integrating RGB imaging and HSI approaches.

Turtles are one of the ancient marine animals that live today. However, the population is threatened with extinction, so its existence needs to be protected and preserved because turtles often eat plastic waste in the ocean whose shape, texture, and color are similar to jellyfish. The technology in the computer vision area can be used to find the solution related to the case of reducing plastics and bottles trash in the ocean by implementing robotics. The region-based Convolutional Neural Network (CNN) is the latest image segmentation and has good detection accuracy based on the Faster R-CNN algorithm. In this study, the training image was built based on two different objects, namely plastic bottles and plastic bags. The target is that the two objects can be recognized even if there are other objects in the vicinity, or the image quality will be affected by the color of the seawater. The results obtained are that plastic objects and bottles can be recognized correctly in the picture. Of the five-color hues tested, the results show that the object detection process is valid on the average color hue, sepia, bandicoot, and grayscale. In contrast, the object detection process is invalid in black-and-white tones. The test results shown in the table explain that the object detection that gets the highest results is an image with normal coloring, while the lowest value is on bandicoot. The average accuracy of all types of images tested is 96.50. However, the accuracy value still needs to be improved to apply feasibility permanently to hardware such as diving robots.

Digital content, such as images, texts, and audio, are now easily accessible on the Internet in a digitalized manner that enables efficient storage and transmission. As information technology evolves concurrently, there has been more cases of cybercrime including data theft and data fabrication by other parties. A wide range of strategies and methods have been used to address these issues using steganography. Steganography is a technique used to prevent unauthorized access of sensitive data by hiding secret information inside digital media containers. This paper aims to investigate the challenges of safely embedding messages into medical images using two different steganographic techniques: Discrete Cosine Transform (DCT) and Least Significant Bit (LSB). An increasingly popular method for hiding sensitive data in the LSBs of pixel values, without causing any discernible deformation is LSB-based steganography. The process of Discrete Cosine Transform alters the structure of the image and embeds the data to enhance its robustness. The DCT and LSB steganography approaches were compared in this work based on the performance parameters. The performance of LSB and DCT methods can be measured by analyzing their SSIM, PSNR, and MSE values. After evaluating different techniques of data hiding in DICOM images, it was found that LSB steganography produces an SSIM value higher than DCT and shows better performance in terms of PSNR values. By observing the results of embedding text and PDF files in DICOM images, it was concluded that LSB steganography provides superior image quality compared to DCT steganography with a data capacity of 2.03 bpp.

Steganography plays a vital role in securing sensitive information within digital communication channels. It has the ability to hide data and protect information effectively without causing disruptions in medical data. The current hospital management systems primarily focus on embedding text and visual in medical images, which presents several challenges, while the integration of audio information remains largely overlooked. This research addresses the security gap by exploring the embedding of audio data in medical images to enhance patient record protection and information integrity. The Proposed work introduced an innovative Steganography approach for medical image data by embedding Audio files aiming to addresses this research gap. This method integrate audio data into medical images, specifically DICOM-standard images without compromising their visual integrity. It also preserves the integrity of DICOM metadata, ensuring compliance with medical imaging standards. The Least Significant Bit (LSB) and Discrete Cosine Transform (DCT) steganography techniques are used to embed audio file data into medical images. The study illustrates the effectiveness of LSB and DCT techniques on a computed tomography(CT) Images. The LSB method is renowned for its simplicity and its ability to extract data without introducing errors. Additionally, the method offers efficient insertion and extraction time during the watermark embedding and retrieval process,making it highly practical for real-time applications. An algorithm employs DCT technique for Audio integration within DICOM images are more robust and imperceptible. Both techniques have been proven to be highly precise and supported by empirical evidence such as PSNR, SSIM, and MSE analysis. Robustness analysis was conducted on various image quality variation scenarios that includes compression level, resolution and noise tolerance. The proposed DCT approach achieves a PSNR of 57.89 dB,SSIM of 0.9997, and MSE of 0.013, demonstrating minimal distortion and superior structural integrity. Robustness analysis shows that DCT outperforms the LSB method, consistently maintaining PSNR above 47 dB, MSE approximately zero, and SSIM at 0.99 across varying compression levels, image resolutions, and noise conditions. After conducting an experiment,the DCT technique is the most suitable approach for secure communication of medical data with capacity of 2.03 bits per pixel (bpp). The overall analysis of proposed work significantly improves result interms of the security and robustness under various attacks.

Cloud computing provides economical and effective solution for sharing data among cloud users with low maintenance cost. The security of data and identity confidentiality while sharing data in multi-owner way cannot be assured by the Cloud Service Providers (CSP's). The Cloud Service Providers are reliable but curious to know the recurrent membership changes in the cloud. In this paper, we propose a secure multi-owner data sharing for dynamic group in the cloud with RSA Chinese Remainder Theorem (RSA-CRT) encryption technique and substring index generation method. RSA-CRT efficiently manages revocation list, key management, with reduced storage and computational overhead. The substring Index generation algorithm reduces the storage space compared to wild card fuzzy alogorithm1