Background Neurodegenerative diseases (NDDs) are becoming a major worldwide issue, especially for the elderly because they are incurable and permanent. It is extremely difficult to provide any medication to people suffering from NDDs. Comprehending essential processes of NDDs are essential to establishing alternative strategies that can increase survival rates in patients. This review is an effort to provide insight into NDDs, innovative therapeutic methods along with their clinical significances and thus provide opportunities for improving therapies for NDDs in the near future. Objective This work aims at a thorough, methodical and critical evaluation of Machine Learning (ML)/Deep Learning (DL) efforts in diagnostics of NDDs, as well as their potential for use in pharmacological, clinical and research settings. An additional objective is to discuss problems and limitations of models, with an eye on furthering research directions. Methods The databases of Elsevier, Sage, Wiley, Springer Link, Emerald Insights and Research Gate were searched for useful assessments of NDDs using ML/DL approaches. Results Numerous potential diagnostic ML/DL models have been suggested and effectively applied to detect NDDs. Biological, neuroimaging and key clinical characteristics in patients have been used to evaluate prognostic models. Additionally, these models provide options for patient categorization, facilitate earlier detections, enhanced diagnosis and better disease outcome predictions for personalized therapies. Conclusion This work points out the rising burden of NDDs on the global elderly while highlighting the significances of ML/DL technological advancements with their limitations for NDDs in diagnostics, identification of effective disease bio-markers and management.
Alzheimer’s disease (AD) is a neurodegenerative disorder that affects a wide range of individuals worldwide. It is of utmost importance to detect AD at an earlier stage and diagnose it to manage the disease effectively. Detecting AD using traditional methodologies is not cost-effective and time-consuming because of the clinical tests and neuroimaging methods involved. Over the last few years, quantum computing and deep learning (DL) have become practical approaches for detecting and diagnosing AD. Unlike conventional methods, quantum computing allows for faster solving complex and entangled computable problems. DL models have a high potential for automatically learning and extracting pertinent features even from larger datasets. Hence, a new approach combining multiple concepts such as deep neural network (DNN), quantum computing, simulated annealing (SA) optimisation, and Haralick feature extraction has been proposed in this work for detecting AD. A quantum deep neural network (QDNN) is introduced in this article to take over the extraordinary computational capability of quantum systems. Haralick feature extraction is implemented in this study to extract the texture features from the medical images, resulting in a rich feature set for the model. The dataset used in this study, The Best Alzheimer’s MRI Dataset contains 11,519 axial MRI images in .jpg format with a resolution of 128 × 128 pixels, categorised into four balanced classes—no impairment, very mild impairment, mild impairment, and moderate impairment—each comprising 2,560 images. To optimise the Haralick features from medical images and to enhance the model’s learning process with optimised parameters, a new feature-specific simulated annealing method (FSSA) has been introduced in this article. The experimental results proved that our model achieved an accuracy of 98%, a precision of 99%, a sensitivity of 97%, and a specificity of 98%. The results achieved in this study are better than the traditional model’s performance, and thus better in all performance metrics. The results indicated that the proposed QDNN model is a good framework for AD detection.
Background The occurrence of pandemics in the last 20 years highlighted the unpreparedness of healthcare systems. There is a worldwide increased trend in the vector borne diseases. Ticks are one of the most common organisms that play a vital role in global ecosystem as well as being vectors of diseases affecting human and livestock. They are able to carry infectious agents that might cause illnesses including paralysis and to some certain extend death. Therefore, it is crucial to identify different genera of ticks to track infectious agents. Conventionally, tick classification is done by acarologists who are experts in the field. For this reason, the identification process is carried out in a difficult and time-consuming manner. Method The aim of the study was to develop a web-based application by using artificial intelligence-based algorithms to easily identify Hyalomma and Rhipicephalus ticks, which are the most abundant genera in Northern Cyprus, with high sensitivity and accuracy. The experimental procedure is structured based on five phases. Phase 1 revolves around data collection in which pictures of 35 identified ticks are taken by experienced acarologists and the curation of non-tick images (spiders, beetles, mites, mosquitos and scorpions). Phase 2 revolves around pre-processing steps and data split. Phase 3 involves training and testing custom Convolutional Neural Network (CNN), Visual Geometry Group 16 (VGG16), Residual Network 50 (ResNet-50) using 6,972 images (3,486 images for each class) for discrimination between ticks and non-ticks and 9,556 images (4,778 images for each class) for the discrimination between Hyalomma and Rhipicephalus. Phase 4 revolves around performance evaluation. Phase 5 is characterized by development of a web-based application (I-TickNet), created to enable a widespread use of the tick classifier. Results The performance evaluation and comparison of the model performance has shown that ResNet50 achieved the best result for binary classification of tick and non-tick (experiment A) with accuracy of 100% and Area Under the Curve (AUC) score of 100%. Moreover, VGG16 achieved the best result for binary classification of ticks (experiment B) with an accuracy of 96.97% and AUC score of 99.55% respectively. All the three models were employed for the development of artificial intelligence/Internet of Things (AI/IoT) framework known as I-TickNet for real-time and on-spot classification of tick images. In conclusion, this study provided a web-based application that can identify two distinct tick genera with high accuracy and sensitivity. The application developed enabled a user-friendly interface to identify genera without requiring any expertise.
Accurate crop yield prediction is vital for ensuring food security and informing agricultural policy, particularly in wheat-dependent regions like Pakistan where manual estimation methods are labor-intensive and imprecise. This study introduces a novel algorithmic framework, MS-YieldStackNet, to predict wheat yield with high spatial resolution by integrating multispectral satellite imagery, in-situ soil analytics, and meteorological variables. A unified feature space is constructed using Normalized Difference Vegetation Index (NDVI) and Difference Vegetation Index (DVI), soil physicochemical attributes, and temporal climate patterns, processed through a stacked ensemble neural architecture (MS-YieldStackNet) combining three parallel feed-forward neural networks (FFNNs) and a Random Forest meta-learner. The model achieved robust performance with an R-squared of 0.81, Mean Squared Error (MSE) of 6,114.30 kg/ha, root mean squared error (RMSE) of 78.19 kg/ha, mean absolute error (MAE) of 59.07 kg/ha, and mean absolute percentage error (MAPE) of 3.55%, demonstrating its potential for precise and scalable crop yield forecasting.
This article introduces Synergistic Gradient Projection with Dynamic Adaptive Risk Expansion (SGP-DARE), a hybrid optimization framework designed to enhance physical-layer security in wireless networks supported by intelligent reflecting surfaces (IRSs). The proposed framework integrates Synergistic Gradient Projection (SGP) for low-complexity joint optimization of base station beamforming and IRS phase shifts, with Dynamic Adaptive Risk Expansion (DARE) ensuring robustness against channel state information (CSI) uncertainties and user mobility. SGP-DARE operates effectively under hardware limitations, including phase quantization, while targeting key objectives such as minimizing secrecy outage probability and improving energy efficiency. Simulation results demonstrate that SGP-DARE significantly outperforms baseline methods in critical metrics of security and efficiency.
