Shoayee Dlaim Alotaibi

Dementia is a degenerative and chronic disorder, increasingly prevalent among older adults, posing significant challenges in providing appropriate care. As the number of dementia cases continues to rise, delivering optimal care becomes more complex. Machine learning (ML) plays a crucial role in addressing this challenge by utilizing medical data to enhance care planning and management for individuals at risk of various types of dementia. Magnetic resonance imaging (MRI) is a commonly used method for analyzing neurological disorders. Recent evidence highlights the benefits of integrating artificial intelligence (AI) techniques with MRI, significantly enhancing the diagnostic accuracy for different forms of dementia. This paper explores the use of AI in the automated detection and classification of dementia, aiming to streamline early diagnosis and improve patient outcomes. Integrating ML models into clinical practice can transform dementia care by enabling early detection, personalized treatment plans, and more effectual monitoring of disease progression. In this study, an Enhancing Automated Detection and Classification of Dementia in Thinking Inability Persons using Artificial Intelligence Techniques (EADCD-TIPAIT) technique is presented. The goal of the EADCD-TIPAIT technique is for the detection and classification of dementia in individuals with cognitive impairment using MRI imaging. The EADCD-TIPAIT method performs preprocessing to scale the input data using z-score normalization to obtain this. Next, the EADCD-TIPAIT technique performs a binary greylag goose optimization (BGGO)-based feature selection approach to efficiently identify relevant features that distinguish between normal and dementia-affected brain regions. In addition, the wavelet neural network (WNN) classifier is employed to detect and classify dementia. Finally, the improved salp swarm algorithm (ISSA) is implemented to choose the WNN technique’s hyperparameters optimally. The stimulation of the EADCD-TIPAIT technique is examined under a Dementia prediction dataset. The performance validation of the EADCD-TIPAIT approach portrayed a superior accuracy value of 95.00% under diverse measures.

Gastrointestinal (GI) cancer detection includes the detection of cancerous or potentially cancerous lesions within the GI tract. Earlier diagnosis is critical for increasing the success of treatment and improving patient outcomes. Medical imaging plays a major role in diagnosing and detecting GI cancer. CT scans, endoscopy, MRI, ultrasound, and positron emission tomography (PET) scans can help detect lesions, abnormal masses, and changes in tissue structure. Artificial intelligence (AI) and machine learning (ML) methods are being gradually applied to medical imaging for cancer diagnosis. ML algorithms, including deep learning methodologies like convolutional neural network (CNN), are applied frequently for cancer diagnosis. These models learn features and patterns from labelled datasets to discriminate between normal and abnormal areas in medical images. This article presents a new Harbor Seal Whiskers Optimization Algorithm with Deep Learning based Medical Imaging Analysis for Gastrointestinal Cancer Detection (HSWOA-DLGCD) technique. The goal of the HSWOA-DLGCD algorithm is to explore the GI images for the cancer diagnosis. In order to accomplish this, the HSWOA-DLGCD system applies bilateral filtering (BF) approach for the removal of noise. In addition, the HSWOA-DLGCD technique makes use of HSWOA with Xception model for feature extraction. For cancer recognition, the HSWOA-DLGCD technique applies extreme gradient boosting (XGBoost) model. Finally, the parameters compared with the XGBoost system can be selected by moth flame optimization (MFO) system. The experimental results of the HSWOA-DLGCD technique could be verified on the Kvasir database. The simulation outcome demonstrated a best possible solution of the HSWOA-DLGCD method than other recent methods.

Quantum software systems represent a new realm in software engineering, utilizing quantum bits (Qubits) and quantum gates (Qgates) to solve the complex problems more efficiently than classical counterparts. Agile software development approaches are considered to address many inherent challenges in quantum software development, but their effective integration remains unexplored. This study investigates key causes of challenges that could hinders the adoption of traditional agile approaches in quantum software projects and develop an Agile-Quantum Software Project Success Prediction Model (AQSSPM). Firstly, we identified 19 causes of challenging factors discussed in our previous study, which are potentially impacting agile-quantum project success. Secondly, a survey was conducted to collect expert opinions on these causes and applied Genetic Algorithm (GA) with Naive Bayes Classifier (NBC) and Logistic Regression (LR) to develop the AQSSPM. Utilizing GA with NBC, project success probability improved from 53.17 to 99.68%, with cost reductions from 0.463 to 0.403%. Similarly, GA with LR increased success rates from 55.52 to 98.99%, and costs decreased from 0.496 to 0.409% after 100 iterations. Both methods result showed a strong positive correlation (rs = 0.955) in causes ranking, with no significant difference between them (t = 1.195, p = 0.240 > 0.05). The AQSSPM highlights critical focus areas for efficiently and successfully implementing agile-quantum projects considering the cost factor of a particular project.

This article aims to address the issues above by defining a social network information transmission model with the amalgamation of explainable artificial intelligence (XAI) compatible with the paranormal connection. It suggests a way of information transmission called local greedy that aids in the preservation of user privacy. Its impact acts as a buffer between the conflicting interests of privacy protection and information dissemination. Aiming at the enumeration problem of seed set selection, an incremental technique is presented for constructing seed sets to minimize time overhead; a local influence subgraph method for computing nodes is also proposed to evaluate the influence of seed set propagation rapidly. The group meets privacy protection conditions. A strategy is presented to determine the upper bound on the likelihood of a node leaking state without resorting to the time-consuming Monte Carlo approach with XAI on the crawled Sina Weibo dataset. The suggested technique is validated experimentally and by example analysis, and the findings demonstrate its usefulness.

The HealthCare (HC) industry has to maintain a large sum of critical medical data. For securing the storage of those data, BlockChain (BC) is used; however, the authorized user cannot easily access the original data, and it also encompasses a storage capacity issue. Although the external DataBase (DB) in BC technology is considered by current research methodologies, it is unsecure. To tackle those issues, this paper secured the diagnosed Parkinson’s Disease (PD) data by BC technology utilizing the 2E2C algorithm. This work takes the Parkinson’s user data to store in BC and detect the status of the patients. Initially, authentication is carried out. After that, the encryption of the data is done by the Enhanced Elliptic Curve Cryptography (2E2C) algorithm. Next, the data are amassed in the external DB of BC by the user’s gateway. Initially, Hospital Management (HM) downloads the data as of the BC and then requests the patient to access the private key for decrypting the data. After that, data pre-processing and Feature Extraction (FE) re performed, then the ISO algorithm selects the vital features. These features are inputted to the Modified Extreme Learning Machine (MELM), which classifies the user’s health status, and the status is stored in the BC; the status is also encrypted. An alert message is sent to the client app if any critical stage is presented in the detection outcome. In an experimental appraisal, the proposed methods’ performance is contrasted with the prevailing research methods.