A5051221287- Chaos-based Image/Signal Encryption
- Cryptographic Implementations and Security
- Cryptography and Data Security
- Coding theory and cryptography
- AI in cancer detection
- Radiomics and Machine Learning in Medical Imaging
- Advanced Steganography and Watermarking Techniques
- Cryptography and Residue Arithmetic
- Complexity and Algorithms in Graphs
- Lanthanide and Transition Metal Complexes
- Biometric Identification and Security
- Advanced MRI Techniques and Applications
- Colorectal Cancer Screening and Detection
- graph theory and CDMA systems
- User Authentication and Security Systems
- Speech and Audio Processing
- Privacy-Preserving Technologies in Data
- Mathematical Dynamics and Fractals
- Digital Media Forensic Detection
- Video Surveillance and Tracking Methods
- Cloud Data Security Solutions
- Text and Document Classification Technologies
- Cellular Automata and Applications
- DNA and Biological Computing
- Image Processing Techniques and Applications
Universiti Tunku Abdul Rahman
2016-2025
Multimedia University
2006-2018
Institute for Infocomm Research
2008-2013
Agency for Science, Technology and Research
2009-2013
Traditional image encryption algorithms transform a plain into noise-like image. To lower the chances for encrypted being detected by attacker during transmission, visually meaningful scheme is suggested to hide using another carrier This paper proposes algorithm that hides secret and digital signature which provides authenticity confidentiality. The recovered used purpose of identity authentication while protect its Least Significant Bit (LSB) method embed on Lifting Wavelet Transform (LWT)...
Gastric cancer is a leading cause of cancer-related deaths worldwide, underscoring the need for early detection to improve patient survival rates. The current clinical gold standard histopathological image analysis, but this process manual, laborious, and time-consuming. As result, there has been growing interest in developing computer-aided diagnosis assist pathologists. Deep learning shown promise regard, each model can only extract limited number features classification. To overcome...
Computer-aided Invasive Ductal Carcinoma (IDC) grading classification systems based on deep learning have shown that may achieve reliable accuracy in IDC grade using histopathology images. However, there is a dearth of comprehensive performance comparisons Convolutional Neural Network (CNN) designs the literature. As such, we would like to conduct comparison analysis seven selected CNN models: EfficientNetB0, EfficientNetV2B0, EfficientNetV2B0-21k, ResNetV1-50, ResNetV2-50, MobileNetV1, and...
The Soil Conservation Service curve number ( S C S-C N) method is one of the most popular methods used to compute runoff amount due its few input parameters. However, recent studies challenged inconsistent results obtained by which set initial abstraction ratio λ as 0.20. This paper developed a watershed-specific N calibration using non-parametric inferential statistics with rainfall–runoff data pairs. proposed first analyzed and generated confidence intervals determine optimum values for S-...
Abstract Most of existing image encryption schemes are proposed in the spatial domain which easily destroys correlation between pixels. This paper proposes an scheme by employing discrete cosine transform (DCT), quantum logistic map and substitution-permutation network (SPN). The DCT is used to images frequency domain. Meanwhile, SPN provide security properties confusion diffusion. provides fast as compared asymmetric based since operations with low computational complexity (e.g.,...
Debates persist regarding the impact of Stain Normalization (SN) on recent breast cancer histopathological studies. While some studies propose no influence classification outcomes, others argue for improvement. This study aims to assess efficacy SN in classification, specifically focusing Invasive Ductal Carcinoma (IDC) grading using Convolutional Neural Networks (CNNs). The null hypothesis asserts that has effect accuracy CNN-based IDC grading, while alternative suggests contrary. We...
Abstract Ensuring the cloud data security is a major concern for corporate subscribers and in some cases private users. Confidentiality of stored can be managed by encrypting at client side before outsourcing it to remote storage server. However, once encrypted, will limit server’s capability keyword search since encrypted server simply cannot make plaintext on data. But again we need functionality efficient retrieval To maintain user’s confidentiality, should able perform over additionally...
SABER is a round 3 candidate in the NIST Post-Quantum Cryptography Standardization process. Polynomial convolution one of most computationally intensive operation Saber Key Encapsulation Mechanism, that can be performed through widely explored algorithms like schoolbook polynomial multiplication algorithm (SPMA) and Number Theoretic Transform (NTT). While SPMA multiplier has slow latency performance, NTT-based usually requires large hardware. In this work, we propose KaratSaber, an optimized...
Cancer is a major global health threat, constantly endangering people's well-being and lives. The application of deep learning in the diagnosis colorectal cancer can improve early detection rates, thereby significantly reducing incidence mortality patients. Our study aims to optimize performance model classification histopathological images assist pathologists improving diagnostic accuracy. In this study, we developed ensemble models based on convolutional neural networks (CNNs) for...
Usually the main primitive in building a secure wireless authentication is cryptographic algorithm, such as digital signature scheme. He et al. proposed handover protocol (IEEE Trans. Wireless Commun., vol. 11, no. 1, 2011) and distributed reprogramming Ind. Electron., 59, 2012) for networks. Both protocols are based on an identity-based scheme which claimed to be yet efficient. Very recently, pointed out that vulnerable key compromised problem. They simple modification fix this problem...