International Journal of Artificial Intelligence

Ensemble Stacking Method of Classifying the Stages of Alzheimer's Disease by using MRI Dataset

2024-12-24T00:40:13+00:00

Alzheimer's Disease (AD) is a progressive neurological disorder that gradually impairs an individual's memory, reasoning, and ability to perform daily tasks. Early and accurate diagnosis of AD is essential for effective intervention, yet remains challenging due to the complexity of its progression. This study explores the use of an ensemble stacking approach to evaluate the effectiveness of transfer learning techniques in classifying various stages of Alzheimer's disease. Unlike traditional methods that directly analyze raw brain images, this research implements a preprocessing technique using the Markov Random Field method to extract the brain tissues specifically affected by AD. These segmented brain tissues are then utilized to train base models, consisting of three convolutional neural networks (CNNs) with varying configurations. The predictions of these base models are ensembled and further refined through a second-level meta-model to enhance classification accuracy. The proposed ensemble stacking framework was evaluated using an MRI dataset obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI), which contains images categorized into Alzheimer’s disease (AD), Mild Cognitive Impairment (MCI), and Healthy Control (HC) groups. The meta-model demonstrated superior performance, achieving an average accuracy of 97%, along with high precision, recall, and F1 scores. This study highlights the potential of ensemble learning and transfer learning in advancing AD diagnosis, offering a robust and efficient approach for categorizing its various stages based on medical imaging data.

The Role of AI in Enhancing Healthcare Access and Service Quality in Resource-Limited Settings

2024-12-24T00:40:09+00:00

The integration of Artificial Intelligence (AI) in healthcare has become a critical factor in improving healthcare delivery, particularly in resource-limited environments. In countries like Pakistan, where healthcare access is a major challenge, AI-powered solutions such as telemedicine, diagnostic tools, and health chatbots have the potential to revolutionize healthcare service delivery. This research aims to explore the effectiveness of AI in improving healthcare access, diagnosis time, and service quality, while identifying the challenges faced in its implementation. A mixed-methods approach was employed, utilizing surveys, interviews, and case studies with healthcare professionals, AI developers, and patients in both rural and urban areas. The findings revealed that AI-driven solutions significantly enhanced healthcare access, particularly in rural areas, by enabling remote consultations and reducing diagnostic time. However, challenges such as infrastructure limitations, low technology literacy, resistance to adoption, and the absence of robust policy frameworks were identified as key barriers to successful AI integration. The study suggests that improvements in technological infrastructure, training, and regulatory frameworks are essential for maximizing the impact of AI in healthcare. Future research should focus on exploring the long-term effects of AI on patient outcomes, investigating the role of policy in AI adoption, and examining how AI can be adapted to different cultural contexts in healthcare systems globally.

Development of an Arabic-Language Virtual Assistant for Public Services to Improve Accessibility of Government Services for Iraqis

2024-12-24T00:40:07+00:00

This research explores the creation of an Arabic-language virtual assistant designed to enhance the accessibility of public services in Iraq. The study centers on developing a chatbot driven by Artificial Intelligence (AI) technologies, especially Natural Language Processing (NLP) and Machine Learning (ML), to help citizens in obtaining government services in Arabic, with a focus on the Iraqi dialect. The chatbot was created to address frequent questions regarding government services like passport renewals, birth registrations, and general inquiries. The system development employed platforms such as Google Dialogflow and TensorFlow to build an intuitive interface that can effectively handle and reply to user inquiries. Data collection comprised Arabic conversational data from Iraqi individuals, obtained via surveys and feedback on government services. The system's effectiveness was assessed through language comprehension accuracy, relevance of responses, and satisfaction of users, with findings indicating high satisfaction levels (88%), accuracy (95%), and relevance (92%). The results indicate that the chatbot greatly improves access to government services, minimizing the necessity for physical visits and increasing service efficiency. Nonetheless, issues regarding the complexities of the Iraqi Arabic dialect and voice recognition capabilities persist. The study finds that the chatbot presents a hopeful approach for addressing language and tech obstacles in providing public services. Future studies should aim at perfecting the language model and boosting voice input functionalities to better the chatbot's performance in Iraq’s public sector.

The Impact of AI Technologies on Precision Agriculture

2024-12-24T00:40:04+00:00

The adoption of artificial intelligence (AI) in precision agriculture offers transformative solutions to challenges such as climate change, resource scarcity, and inefficient traditional farming methods. This study evaluates the application of AI in improving crop health monitoring, yield prediction, and optimizing the use of natural resources like water and fertilizers. A quantitative research design was employed, utilizing field experiments and data collected from soil sensors, drones, and AI-based tools across ten diverse agricultural locations in Pakistan. The findings demonstrate that AI enables early detection of crop diseases and stress conditions, reducing response time and improving overall crop health. Predictive models powered by AI provide highly accurate yield estimations, facilitating better planning and resource allocation. Additionally, AI technologies optimize water and fertilizer usage, achieving reductions of up to 15% and 10%, respectively, without compromising crop yields. Despite technical and infrastructural challenges, the results underscore the potential of AI in enhancing sustainability and efficiency in agriculture. To maximize these benefits, collaboration between governments and private sectors is crucial in providing training, infrastructure, and region-specific solutions for farmers. Future research should explore integrating AI with automation technologies to further improve agricultural practices, including harvesting and distribution processes. This study highlights the importance of AI as a key enabler of sustainable food production and agricultural resilience.

A Proposed Multilayer Perceptron Model and Kernel Principal Analysis Component for the Prediction of Chronic Kidney Disease

2024-12-24T00:40:00+00:00

unfortunately, this stage is mostly detected at a late stage, leading to dialysis or transplantation. Early detection is important for the effective management of CKD. ML has shown success in the early prediction of CKD by using an algorithm that learns and predicts without being programmed. ML requires appropriate datasets for this process, and one of the aspects is dimensionality reduction, which addresses the challenges of unnecessary tests, high-cost tests and the use of redundant tests. Principal Component Analysis (PCA) is a widely used method for dimensionality reduction; however, it relies on linear transformation to identify relationships within features. Medical datasets such as CKD exhibit complex nonlinear features, which is important for exploring alternative dimensionality reduction methods that can rely on nonlinear transformation. This study aims to propose an ML approach that utilises kernel PCA to reduce dimensionality based on nonlinearity structures and enhance the prediction of CKD. We evaluated seven ML models on the different kernel functions of PCA. The ML models included random forest (RF), decision tree (DT), multilayer perceptron (MLP), support vector machine (SVM), extreme gradient boosting (XgBoost), adaptive boosting (AdaBoost), logistic regression (LR), and gradient boosting. The kernel functions used for dimensionality reduction are cosine principal component analysis (CPCA), polynomial principal component analysis (PPCA), radial basis principal component analysis (RPCA), sigmoid principal component analysis (SPCA) and linear principal component analysis (LPCA). The results of the study revealed that the MLP with RPCA, SPCA and CPCA achieved good performance in predicting CKD, with an accuracy score of 99% on DB1, and that the MLP with RPCA and SPCA achieved good performance in predicting CKD, with an accuracy score of 100% on DB2. The study showed how kernel PCA, which effectively reduces high dimensionality-based nonlinearity relationships, can positively affect the performance of predictive models and the power of dimensionality reduction toward disease prediction.