Objectives: With the help of Artificial Intelligence, the analysis and comparison of unknown bite marks will become more accurate and reliable. The purpose of this study is to create and validate a Convolutional Neural Network (CNN) model for determining the age and sex of individuals from bite mark samples.

Methods: A dataset comprising 50 bite mark images (25 males and 25 females) from individuals belonging to the 18-25 age category was collected and analyzed using the CNN’s model.

Results and Discussion: The result shows that the CNN’s model has high accuracy and strong generalization capabilities in the process of classification of bite marks on the basis of sex and age, and the accuracy in sex determination is 97% and in the case of age determination in male it is again 97% and age determination in case of female it is 98%. The performance of this model of architecture indicates that it can serve as a potential tool for the process of investigation and make the identification of the individuals who were involved in the crime more easily. The precision and accuracy of this method is very high due that it can assist in the process more effectively and efficiently. By determining the age and sex of an unknown bite mark, the list of the suspected individuals can be narrowed down and it is very helpful for the investigation process.

Conclusion: These findings indicate that the CNN model can be used as a valuable technique in forensic investigations, offering a novel, AI-based approach to improve the accuracy and precision of bite mark analysis for age and sex determination. This study also paves the path for additional study and development in AI-driven forensic science.

Objective: This review explores the utilization of a computer-based model in the recognition and quality control of herbals and their adulterants. The study highlights artificial intelligence's power to transform the herbal industry by improving quality control, therapeutic reproducibility, and stakeholder accessibility.

Methods: The paper examines recent advanced computational methods for identifying herbals. Artificial intelligence addresses issues such as data complications and adulterant recognition. The paper also compares artificial intelligence-based methods with traditional approaches, focusing on their benefits in speed, cost-effectiveness, and precision.

Results and Discussion: Artificial intelligence methods show significant power in the herbal field. Their use improves herbal recognition, adulterant discovery, and quality assurance by leveraging data-driven algorithms. Moreover, artificial intelligence decreases laboratory expenses and increases the convenience and suitability of herbals.

Conclusion: Artificial intelligence provides transformative solutions for the herbal industry by addressing venerable challenges in herbal identification and adulterant detection. Its interdisciplinary approach promises better regularity, increased remedial outcomes, and increased trust of consumers.

Over the past decade, significant advancements have addressed these barriers. Schemes such as BGV, BFV, and CKKS have been developed for efficient integer and approximate real-number computations. Algorithmic innovations like optimized bootstrapping and improved noise management have reduced complexity. Hardware acceleration using GPUs and FPGAs has enhanced performance, while integration with secure multi-party computation and zero-knowledge proofs has broadened HE’s applicability.

Applications now span privacy-preserving machine learning, genomic data analysis, and financial analytics. Toolkits such as SEAL, HElib, and PALISADE have improved accessibility for developers and researchers. Despite progress, challenges remain, including balancing efficiency and security, and improving usability for non-experts.

The article also explores HE’s reliance on lattice-based problems like Learning With Errors (LWE) and Ring-LWE, which provide quantum resistance. As hybrid cryptographic models emerge, HE is increasingly recognized as a key component in securing sensitive data in the postquantum era.

This review highlights HE’s maturation from a theoretical concept to a practical solution, demonstrating its potential as a cornerstone for secure, privacy-preserving computing across industries.

This paper focuses on how AI can enhance systems engineering. Historical experience has shown that the successful introduction of a new technology, e.g., manufacturing robots, requires that existing processes be re-engineered to leverage the advances of that technology. This paper presents a re-engineering framework of the four stages of systems engineering, highlighting opportunities for the effective integration of artificial intelligence.

Methods: In this study, a Convolutional Neural Network (CNN) architecture, named ALZNetwork, is proposed for diagnosing Alzheimer’s Disease (AD). The model’s robustness lies in its training on a single dataset and testing on two different Magnetic Resonance Imaging (MRI) datasets, both consisting of 2D slices from Alzheimer’s Disease Neuroimaging Initiative (ADNI) sources, achieving impressive results. There were two main objectives of this research: (1) to create a novel 2D image dataset, and (2) to construct a robust convolutional framework on this dataset for AD diagnosis.

Results: Comparisons were made between the ALZ-Network model and its pre-trained counterparts, i.e., Xception, InceptionV3, and EfficientNetB0. Model evaluation was done on a 3-class classification problem using standard metrics, i.e., accuracy, positive predictive value, sensitivity, and the harmonic mean of the latter two. InceptionV3 and Xception models achieved reduced training time with classification accuracies of 91.69% and 97.68%, respectively, whereas EfficientNetB0 and ALZ-Network achieved higher classification accuracies of 99.32% and 99.70%, respectively.

Discussion: A web platform, i.e., Alzheimer’s Disease Detection System (ADDS), built on the proposed architecture and other models, was created (run on a local machine) to test unseen 2D images of AD.

Conclusion: This platform can assist radiologists in screening for potential Alzheimer’s disease from MRI scans of subjects.

Method: This paper proposes the RSAFF network, which incorporates a residual self-attention module to enhance edge information extraction and an RFA_a module for feature recalibration and gradient preservation.

Results: The proposed method achieved a dice similarity coefficient of 91.52% on the test set, exceeding U-Net by 2.01% and outperforming other comparative models.

Discussion: The improvement can be attributed to the enhanced ability to capture fine anatomical structures and edge details through self-attention and feature fusion mechanisms.

Conclusion: The RSAFF model demonstrates significant potential for improving the accuracy of spine CT image segmentation in clinical applications.