No abstract

No abstract

No abstract

Due to the wide availability of easy-to-access content on social media, along with the advanced tools and inexpensive computing infrastructure, has made it very easy for people to produce deep fakes that can cause to spread disinformation and hoaxes. This rapid advancement can cause panic and chaos as anyone can easily create propaganda using these technologies. Hence, a robust system to differentiate between real and fake content has become crucial in this age of social media. This paper proposes an automated method to classify deep fake images by employing Deep Learning and Machine Learning based methodologies. Traditional Machine Learning (ML) based systems employing handcrafted feature extraction fail to capture more complex patterns that are poorly understood or easily represented using simple features. These systems cannot generalize well to unseen data. Moreover, these systems are sensitive to noise or variations in the data, which can reduce their performance. Hence, these problems can limit their usefulness in real-world applications where the data constantly evolves. The proposed framework initially performs an Error Level Analysis of the image to determine if the image has been modified. This image is then supplied to Convolutional Neural Networks for deep feature extraction. The resultant feature vectors are then classified via Support Vector Machines and K-Nearest Neighbors by performing hyper-parameter optimization. The proposed method achieved the highest accuracy of 89.5% via Residual Network and K-Nearest Neighbor. The results prove the efficiency and robustness of the proposed technique; hence, it can be used to detect deep fake images and reduce the potential threat of slander and propaganda.

Background Diabetes Mellitus and periodontitis are chronic diseases with known reciprocal association. Studies have shown that uncontrolled diabetes increases the risk of development and progression of periodontal disease. This study aimed to explore the association and severity of periodontal clinical parameters and oral hygiene with HbA1c levels in non-diabetics and T2DM patients. Materials and methods In this cross-sectional study, the periodontal status of 144 participants, categorized into non-diabetics, controlled T2DM, and uncontrolled T2DM and were assessed via the Community Periodontal Index (CPI), Loss of Attachment Index (LOA index), and the number of missing teeth, while oral hygiene was measured by utilizing the Oral Hygiene Index Simplified (OHI-S). SPSS was used for data analysis. Chi-square test was used to find out the association of different independent variables with HbA1c groups, while ANOVA and post-hoc tests were run for inter-group and intra-group comparison respectively. Results Out of 144 participants, the missing dentition was prevalent in uncontrolled T2DM with mean 2.64 ± 1.97 (95% CI 2.07–3.21; p = 0.01) followed by controlled T2DM 1.70 ± 1.79 (95% CI 1.18–2.23; p = 0.01) and non-diabetics 1.35 ± 1.63 (95% CI 0.88–1.82; p = 0.01) respectively. Furthermore, non-diabetics had a higher proportion of CPI score 0 (Healthy) [30 (20.8%); p = 0.001] as compared to uncontrolled T2DM [6 (4.2%); p = 0.001], while CPI score 3 was more prevalent in uncontrolled T2DM in comparison to non-diabetics. Loss of attachment (codes-2,3 and 4) was also frequently observed in uncontrolled T2DM compared to non-diabetics (p = 0.001). Similarly, based on Oral Hygiene Index- Simplified (OHI-S), the result showed that poor oral hygiene was most commonly observed in uncontrolled T2DM 29 (20.1%) followed by controlled T2DM patients 22 (15.3%) and non-diabetic [14 (9.7%); p = 0.03]. Conclusion This study showed that periodontal status and oral hygiene status were deteriorated in uncontrolled T2DM patients compared to non-diabetic participants and controlled T2DM.