Review of Computer Engineering Research

Detection and localization of wrist fractures in x-ray imagery using deep learning teaching

Haider Abdulbaqi Abbas Mohammed — 2024-08-06

Hospitals often refer patients with wrist fractures, particularly to their emergency rooms. To accurately diagnose these illnesses and choose the appropriate course of therapy, doctors must evaluate images from various medical equipment, medical data, and a physical assessment of the patient. This project attempts to use deep learning on these images to identify wrist X-ray fractures and help physicians diagnose them, particularly in emergency departments. This study employs a dataset comprising both fractured and regular wrists to assess the extent to which the Recurrent Neural Network with 22 Convolutional Neural Network layers (RN22-CNNs) transfers knowledge for fracture identification and classification. We evaluate the diagnostic accuracy of the RN-21CNN model against four popular transfer learning models, namely Visual Geometry Group (Vgg16), ResNet-50, Inception V3, and Vgg19. We used the model on a dataset of 1644 X-rays collected from the Kaggle repository. Next, we trained, verified, and tested the adapted (RN22-CNNs) model. The proposed model had an accuracy of 96.61%. The proposed Computer-Aided Diagnosis System (CADS) will save medical practitioners' burden by accurately identifying fractures.

Utilization of IoT and database system of central warehouse project in the pharmaceutical industry

Edi Susanto — 2024-10-21

This study aims to develop an MRPII device that utilizes internet technology for inventory management control processes, using case studies from pharmacutical companies in Indonesia. The research was conducted using field observation methods and system development, then comparing the manual system and MRPII. An internet-based inventory management system was created by integrating the warehouse’s material database into each material code via a QR. code. The study found that implementing the MRP II system design increases work effectiveness and reduces the risk of errors that frequently occur in conventional systems. Moreover, using the MRPII can facilitate the audit process and establish transparency in the inventory management process. Data processed using IoT is generated faster and more accurately as company operations improve quality, reduce unnecessary activities, and make it easier to organize materials and run administrative and technical processes in inventory management; it is measured based on reach, workforce requirements, supply, and handling time. In the industrial world, the MRPII database system has the potential to evolve into several more complex and comprehensive systems. It has broad integration and can assist humans working across all lines, particularly in the data processing system.

Locust-based genetic classifier for abnormality identification in brain

Soundararajan Mohanalakshmi — 2024-10-21

This study investigates the loctus-based genetic classifier for abnormality identification in the brain. In medical care, clinical professionals have to spend a lot of time extracting, identifying, and segmenting the afflicted region from magnetic resonance brain images. Utilizing computer-aided approaches is crucial to overcome this restriction. Henceforth, this paper proposes an efficient classifier for diagnosing abnormalities in human brain using magnetic resonance images (MRI). The focus is on improving the accuracy and efficiency of medical image segmentation, specifically for brain tumours, to assist clinical professionals in early disease detection. In order to improve the image's quality through noise reduction, the Gaussian filter is employed during the pre-processing stage. The proposed tumour segmentation is based on the Otsu algorithm, and the gray-level co-occurrence matrix (GLCM) is used to extract the relevant features. In this work, the locust-based genetic classifier plays a crucial role in early brain disease identification and pinpointing the precise location of the damaged area. Accuracy, sensitivity, and specificity have been used to analyze and validate the outcomes of the proposed technique. The current study's findings indicate accurate prediction of brain abnormality and have a 98.9% accuracy rate, 97.2% specificity, and 96% sensitivity. The study presents a reliable and efficient method for diagnosing brain abnormalities using MRI. The combination of the proposed approaches significantly enhances the segmentation and classification processes, leading to high diagnostic accuracy. This approach offers practical benefits for clinical professionals by reducing the time and effort required for diagnosing brain abnormalities.

Overview of homomorphic encryption technology for data privacy

Qiang Chen — 2024-10-25

This study examines the overview of homomorphic encryption technology for data privacy. In the era of big data, the growing need to utilize vast amounts of information while ensuring privacy and security has become a significant challenge. Homomorphic encryption technology has gained attention as a solution for privacy-preserving data processing, allowing computations on encrypted data without exposing sensitive information. This study introduces the concept of data privacy preservation and explores the evaluation of homomorphic encrypted technology. The focus is on analyzing both partial and full homomorphic encryption methods, highlighting their respective characteristics, evaluation criteria, and the current state of research. Partial homomorphic encryption supports limited operations, while full homomorphic encryption enables unlimited computation on encrypted data, though both face challenges related to computational overhead and efficiency. Additionally, this paper addresses the ongoing issues and limitations associated with homomorphic encryption, such as its complexity, large encryption volumes, and difficulties in handling large-scale datasets. Despite these challenges, researchers continue to refine the technology and expand its applications in cloud computing, big data analytics, and privacy-preserving computing environments. This study also discussed potential future research avenues aimed at improving the scalability, efficiency, and security of homomorphic encryption to support broader, real-world applications. Ultimately, homomorphic encryption is positioned as a key enabler for secure data utilization in an increasingly privacy-conscious digital landscape.