The rapid developments of storage technology and information exchange encourage the development of research in the field of information security. In the process of sending information, tamper and issues about data ownership may occur. The fragile watermarking is one technique that can overcome the problem, in which this technique exploits sensitivity to tamper with the inserted watermark components. Therefore, it is not tolerable to change even only one bit. Self-embedding can be defined as some important features obtained from a selected image as a watermark by modifying the pixel value of the original image. Once a picture which has been inserted with a watermark is modified by other users, it can be used for tamper detection and recovery images. Due to the importance of this fragile watermarking scheme, this paper discusses the principles and characteristics of a fragile watermarking algorithm. The main contribution of this paper survey is that it summarises the current mechanisms of selection, generation, method of watermark insertion, detection and tamper localisation and recovery procedures. Comparison of several watermarking techniques was analysed and presented in tabular form, as well as experimental evaluation of four watermarking schemes in many graphs to show the performance of the self-embedding fragile watermarking scheme.

Corona is a very contagious virus. In a pandemic like this, people often worry whether they are infected or not. When they cough, they often worry whether it is a sign of covid-19 or an ordinary cough. From the clinical symptoms can actually be known whether someone has Covid or not. In this study, a clinical symptom dataset will be used to classify the symptoms using a Decision Tree algorithm. The decision trees used in this research are J48 and Hoeffding Tree. Decision Tree is one of the most popular classification methods because it is easy to interpret by Humans. the prediction model uses a hierarchical structure. The concept is to convert data into decision trees or decision rules. the result of J48 were slightly better than the Hoeffding tree in terms of accuracy, precision, and recall. Meanwhile, from the tree view results, the Hoeffding Tree is simpler and the number of nodes is less than J48.

This paper proposes a dual watermarking scheme that can integrate the functions of authentication, copyright protection, and image recovery in the same cover image. The robust watermarking utilizes a single watermark using the discrete cosine transform (DCT) domain for copyright protection, while the fragile scheme utilizes two self-embedding watermarks in a spatial domain for authenticating and restoring digital image content. The mechanism of the two schemes is carried out sequentially and uses a block-based approach. A new blind robust watermarking is proposed using a quantitative property of intermediate frequency coefficient for embedding and adaptive embedding strength selection to balance transparency and robustness. Fragile watermarks are inserted into a robust watermarked image based on the improved replacement approach of the least significant bits. Experimental results show that the proposed method can withstand various processing attacks; enhance the accuracy of deceptive localization with good visual quality of image recovery.