Mobile and Forensics

Image Forensics Using Error Level Analysis and Block Matching Methods

Iis Sudianto — 2024-08-08

The development of image editing tools today makes everyone able to manipulate images easily so that many images are doubtful of their authenticity. The current image can be used as evidence in a legal case in court. The authenticity of the image is a topic that many have tried to solve various studies. This study discusses the authenticity of the image using the Error Level Analysis (ELA) method to determine the authenticity of the image, especially in the JPEG image. Block Matching is used in the process of dividing an image into several square or block parts. The ELA method has been successfully implemented with 95% image compression resulting in MSE and PSNR values in distinguishing the edited image. The average MSE is 23.8 dB and the average PSNR is 34.47 dB. Block Matching results as a whole show that the pixel value for x values that reach 30 there are 9 images, x values that reach 24 there are 9 images, x values that reach 23 there are 1 image, and for x values that reach 19 there is 1 image. The result of pixel (y) of all images exceeds the value of 12 which in pixel (y) undergoes many changes marked by the presence of white spots.

Identification of Plasmodium Vivax in Blood Smear Images Using Otsu Thresholding Algorithm

Nurul Huda — 2024-09-18

In this research, we explore the efficacy of Convolutional Neural Networks (CNN) and Support Vector Machines (SVM) in identifying Plasmodium vivax from blood smear images. We utilized a dataset comprising images of Plasmodium vivax and non-infected cells, applying CNN for deep feature extraction and SVM with otsu’s thresholding for segmentation. The dataset was preprocessed and augmented to enhance model performance. The CNN architecture, consisting of multiple convolutional and dense layers, achieved an accuracy of 98.46% on the validation set. For comparison, features extracted using Otsu’s Thresholding were fed into an SVM classifier, yielding an accuracy of 82%. Confusion matrix was generated to evaluate the classification performance of both models. The CNN model demonstrated superior accuracy and robustness in classification tasks compared to the SVM model. This research shows how deep learning frameworks can be used to analyse medical images and how important it is to have methods for extracting and choosing features to make machine learning models work better.

National Institute of Standard Technology Approach for Steganography Detection on WhatsApp Audio Files

Abdul Haris Muhammad — 2024-09-18

Audio steganography in instant messaging applications such as WhatsApp poses new challenges in the field of digital security, especially due to the ability to hide data in frequently used formats. This research examines the effectiveness of steganography detection on WhatsApp audio files by applying a method developed by the National Institute of Standards and Technology (NIST). This approach was chosen due to its reputation in security testing standards, but its use in the context of audio steganography on instant messaging platforms has not been widely explored. The novelty of this research lies in the adaptation of the NIST method specifically for audio steganography analysis in WhatsApp, which includes testing against various compression and end-to-end encryption scenarios. The main findings of this research show that the NIST method successfully improves the accuracy of hidden message detection compared to conventional steganalysis techniques, especially under the condition of compressed audio files. In addition, this research also found that the integration of the NIST method enables more effective detection of steganographic data in encrypted audio files. These results confirm that the NIST method can be successfully adapted for instant messaging applications such as WhatsApp, making a significant contribution in the improvement of digital security. This research not only identifies weaknesses in existing steganography techniques, but also introduces a new framework for more accurate and efficient detection in encrypted environments.

Rediscover Story Of Muhammadiyah Through 3D Game By Applying Game Development Life Cycle

Achmad Nur Hafizh — 2024-09-20

Though specifically in Indonesia, Muhammadiyah is already well known but there are still some who do not know their history. This makes people that do not know about Muhammadiyah and the history behind it to make unfounded assumptions about the Islamic refined organization. The purpose is to make an educational game based on Muhammadiyah Museum to further increase the wisdom of players about Muhammadiyah’s history and also to remember and know the history behind each artifact is visualized in form of a game to increase the player’s knowledge. The game development for players will be developed using the Game Development Life Cycle (GDLC) methodology and mostly the modelling technique that will be used is mesh modelling technique in Blender. Each step of this methodology is fitting for the game development and the step might be skipped or swapped according to the needs of research. There are 2 black box tests conducted, the first black box test that has 15 functions result is 47% in accordance with several bugs found which was fixed in the second black box test that resulted 87% in accordance, 13% not in accordance because of the feature was not yet implemented but listed in the main menu. The second test conducted which results and practicality of this educational game using the System Usability Scale (SUS) which consists of 10 instrument statements were scored 85.3 which means that this educational game was declared excellent and acceptable.

Hybrid ABC–K Means for Optimal Cluster Number Determination in Unlabeled Data

Harunur Rosyid — 2024-09-30

This study presents the ABC K Means GenData algorithm, an enhancement over traditional K Means clustering that integrates the Artificial Bee Colony (ABC) optimization approach. The ABC K Means GenData algorithm addresses the issue of local optima commonly encountered in standard K Means algorithms, offering improved exploration and exploitation strategies. By utilizing the dynamic roles of employed, onlooker, and scout bees, this approach effectively navigates the clustering space for categorical data. Performance evaluations across several datasets demonstrate the algorithm's superiority. For the Zoo dataset, ABC K Means GenData achieved high Accuracy (0.8399), Precision (0.8089), and Recall (0.7286), with consistent performance compared to K Means and Fuzzy K Means. Similar results were observed for the Breast Cancer dataset, where it matched the Accuracy and Precision of K Means and surpassed Fuzzy K Means in Precision and Recall. In the Soybean dataset, the algorithm also performed excellently, showing top scores in Accuracy, Precision, Recall, and Rand Index (RI), outperforming both K Means and Fuzzy K Means.. The comprehensive results indicate that ABC K Means GenData excels in clustering categorical data, providing robust and reliable performance. Future research will explore its application to mixed data types and social media datasets, aiming to further optimize clustering techniques.

Design Job Vacancy Website Using The Laravel Framework

Moch Farid Fauzi — 2024-10-26

Job vacancies are the most sought after during the current COVID-19 pandemic—the number of layoffs by companies experiencing problems in their business. Many people become unemployed, and income levels decrease while their needs must still be met. This has an impact on the number of people looking for job vacancies. Often found job seekers and job seekers seeking information still through mass media, banners, posters, billboards, and word of mouth. This search and recruitment model will not be efficient and will not be right on target. The solution offered to overcome these problems is to create a website for job vacancies, recruitment, and job applications. The research method used is Rapid Application Development (RAD) to find out the website creation process carried out in a short and influential period. The research flow is looking for references, determining project needs by making UI design and database design, making prototypes, testing, refining, developing features, feedback questionnaires, and project implementation. This research resulted in a job vacancy website called "AntiNggur". This website is expected to facilitate the dissemination of information on job vacancies, the job search process, and the process of recruiting new workers that are more effective and more targeted.