A Systematic Survey on Energy-Efficient Techniques in Sustainable Cloud Computing

Sustainability, Journal Year: 2022, Volume and Issue: 14(10), P. 6256 - 6256

Published: May 20, 2022

Global warming is one of the most compelling environmental threats today, as rise in energy consumption and CO2 emission caused a dreadful impact on our environment. The data centers, computing devices, network equipment, etc., consume vast amounts that thermal power plants mainly generate. Primarily fossil fuels like coal oils are used for generation these induce various problems such global ozone layer depletion, which can even become cause premature deaths living beings. recent research trend has shifted towards optimizing green fields since world recognized importance concepts. This paper aims to conduct complete systematic mapping analysis high cloud centers its effect To answer questions identified this paper, hundred nineteen primary studies published until February 2022 were considered further categorized. Some new developments taxonomy efficiency techniques have also been discussed. It includes VM Virtualization Consolidation, Power-aware, Bio-inspired methods, Thermal-management techniques, an effort evaluate center’s role reducing footprints. Most researchers proposed software level with massive infrastructures not required compared hardware it less prone failure faults. Also, we disclose some dominant provide suggestions future enhancements computing.

Language: Английский

---

A Review of Deep Transfer Learning Approaches for Class-Wise Prediction of Alzheimer’s Disease Using MRI Images

Archives of Computational Methods in Engineering, Journal Year: 2023, Volume and Issue: 30(4), P. 2409 - 2429

Published: Jan. 3, 2023

Language: Английский

---

An Explainable AI Paradigm for Alzheimer’s Diagnosis Using Deep Transfer Learning

Diagnostics, Journal Year: 2024, Volume and Issue: 14(3), P. 345 - 345

Published: Feb. 5, 2024

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that affects millions of individuals worldwide, causing severe cognitive decline and memory impairment. The early accurate diagnosis AD crucial for effective intervention management. In recent years, deep learning techniques have shown promising results in medical image analysis, including from neuroimaging data. However, the lack interpretability models hinders their adoption clinical settings, where explainability essential gaining trust acceptance healthcare professionals. this study, we propose an explainable AI (XAI)-based approach disease, leveraging power transfer ensemble modeling. proposed framework aims to enhance by incorporating XAI techniques, allowing clinicians understand decision-making process providing valuable insights into diagnosis. By popular pre-trained convolutional neural networks (CNNs) such as VGG16, VGG19, DenseNet169, DenseNet201, conducted extensive experiments evaluate individual performances on comprehensive dataset. ensembles, Ensemble-1 (VGG16 VGG19) Ensemble-2 (DenseNet169 DenseNet201), demonstrated superior accuracy, precision, recall, F1 scores compared models, reaching up 95%. order transparency diagnosis, introduced novel model achieving impressive accuracy 96%. This incorporates saliency maps grad-CAM (gradient-weighted class activation mapping). integration these not only contributes model’s exceptional but also provides researchers with visual regions influencing Our findings showcase potential combining realm paving way more interpretable clinically relevant healthcare.

Language: Английский

---

Machine and deep learning approaches for alzheimer disease detection using magnetic resonance images: An updated review

Measurement, Journal Year: 2024, Volume and Issue: 226, P. 114100 - 114100

Published: Jan. 4, 2024

Language: Английский

---

Supervised Machine Learning Empowered Multifactorial Genetic Inheritance Disorder Prediction

Computational Intelligence and Neuroscience, Journal Year: 2022, Volume and Issue: 2022, P. 1 - 10

Published: May 31, 2022

Fatal diseases like cancer, dementia, and diabetes are very dangerous. This leads to fear of death if these not diagnosed at early stages. Computer science uses biomedical studies diagnose diabetes. With the advancement machine learning, there various techniques which accessible predict prognosis based on different datasets. These datasets varied (image CSV datasets) around world. So, is a need for some learning classifiers in human. In this paper, we used multifactorial genetic inheritance disorder dataset Several separately with help types multiclass classification proposed methodology support vector (SVM) K-nearest neighbor (KNN) three compared accuracy. Simulation results have shown that model SVM KNN prediction from achieved 92.8% 92.5%, 91.2% accuracy during training testing, respectively. it observed SVM-based (MGIDP) give attractive as KNN. The application helps before time plays vital role minimize ratio

Language: Английский

---

Modified Self-Adaptive Bayesian Algorithm for Smart Heart Disease Prediction in IoT System

Sustainability, Journal Year: 2022, Volume and Issue: 14(21), P. 14208 - 14208

Published: Oct. 31, 2022

Heart disease (HD) has surpassed all other causes of death in recent years. Estimating one’s risk developing heart is difficult, since it takes both specialized knowledge and practical experience. The collection sensor information for the diagnosis prognosis cardiac a application Internet Things (IoT) technology healthcare organizations. Despite efforts many scientists, diagnostic results HD remain unreliable. To solve this problem, we offer an IoT platform that uses Modified Self-Adaptive Bayesian algorithm (MSABA) to provide more precise assessments HD. When patient wears smartwatch pulse device, records vital signs, including electrocardiogram (ECG) blood pressure, sends data computer. MSABA used determine whether been obtained normal or abnormal. retrieve features, kernel discriminant analysis (KDA) used. By contrasting suggested with existing models, can summarize system’s efficacy. Findings like accuracy, precision, recall, F1 measures show MSABA-based prediction system outperforms competing approaches. method demonstrates achieves highest rate accuracy compared classifiers largest possible amount data.

Language: Английский

---

A Novel Approach Utilizing Machine Learning for the Early Diagnosis of Alzheimer's Disease

Deleted Journal, Journal Year: 2023, Volume and Issue: 1(2), P. 882 - 898

Published: April 10, 2023

Alzheimer's disease (AD) is one of the leading causes dementia among older people. In addition, a considerable portion world's population suffers from metabolic problems, such as and diabetes. affects brain in degenerative manner. As elderly grows, this illness can cause more people to become inactive by impairing their memory physical functionality. This might impact family members financial, economic, social spheres. Researchers have recently investigated different machine learning deep approaches detect diseases at an earlier stage. Early diagnosis treatment AD help patients recover it successfully with least harm. paper proposes model that comprises GaussianNB, Decision Tree, Random Forest, XGBoost, Voting Classifier, GradientBoost predict disease. The trained using open access series imaging studies (OASIS) dataset evaluate performance terms accuracy, precision, recall, F1 score. Our findings showed voting classifier attained highest validation accuracy 96% for dataset. Therefore, ML algorithms potential drastically lower annual mortality rates through accurate detection.

Language: Английский

---

Explainable AI-based Alzheimer’s prediction and management using multimodal data

PLoS ONE, Journal Year: 2023, Volume and Issue: 18(11), P. e0294253 - e0294253

Published: Nov. 16, 2023

Background According to the World Health Organization (WHO), dementia is seventh leading reason of death among all illnesses and one causes disability world’s elderly people. Day by day number Alzheimer’s patients rising. Considering increasing rate dangers, disease should be diagnosed carefully. Machine learning a potential technique for diagnosis but general users do not trust machine models due black-box nature. Even, some those provide best performance because using only neuroimaging data. Objective To solve these issues, this paper proposes novel explainable prediction model multimodal dataset. This approach performs data-level fusion clinical data, MRI segmentation psychological However, currently, there very little understanding five-class classification disease. Method For predicting five class classifications, 9 most popular Learning are used. These Random Forest (RF), Logistic Regression (LR), Decision Tree (DT), Multi-Layer Perceptron (MLP), K-Nearest Neighbor (KNN), Gradient Boosting (GB), Adaptive (AdaB), Support Vector (SVM), Naive Bayes (NB). Among RF has scored highest value. Besides explainability, SHapley Additive exPlanation (SHAP) used in research work. Results conclusions The evaluation demonstrates that classifier 10-fold cross-validation accuracy 98.81% disease, cognitively normal, non-Alzheimer’s dementia, uncertain others. In addition, study utilized Explainable Artificial Intelligence based on SHAP analyzed prediction. our knowledge, we first present (Clinical, Psychological, data) Open Access Series Imaging Studies (OASIS-3) Besides, patient management architecture also proposed

Language: Английский

---

Edge AI for Early Detection of Chronic Diseases and the Spread of Infectious Diseases: Opportunities, Challenges, and Future Directions

Future Internet, Journal Year: 2023, Volume and Issue: 15(11), P. 370 - 370

Published: Nov. 18, 2023

Edge AI, an interdisciplinary technology that enables distributed intelligence with edge devices, is quickly becoming a critical component in early health prediction. AI encompasses data analytics and artificial (AI) using machine learning, deep federated learning models deployed executed at the of network, far from centralized centers. careful analysis large datasets derived multiple sources, including electronic records, wearable demographic information, making it possible to identify intricate patterns predict person’s future health. Federated novel approach further enhances this prediction by enabling collaborative training on devices while maintaining privacy. Using computing, can be processed analyzed locally, reducing latency instant decision making. This article reviews role highlights its potential improve public Topics covered include use algorithms for detection chronic diseases such as diabetes cancer computing detect spread infectious diseases. In addition discussing challenges limitations prediction, emphasizes research directions address these concerns integration existing healthcare systems explore full technologies improving

Language: Английский

---

Should artificial intelligence be used in conjunction with Neuroimaging in the diagnosis of Alzheimer’s disease?

Frontiers in Aging Neuroscience, Journal Year: 2023, Volume and Issue: 15

Published: April 18, 2023

Alzheimer’s disease (AD) is a progressive, neurodegenerative disorder that affects memory, thinking, behavior, and other cognitive functions. Although there no cure, detecting AD early important for the development of therapeutic plan care may preserve function prevent irreversible damage. Neuroimaging, such as magnetic resonance imaging (MRI), computed tomography (CT), positron emission (PET), has served critical tool in establishing diagnostic indicators during preclinical stage. However, neuroimaging technology quickly advances, challenge analyzing interpreting vast amounts brain data. Given these limitations, great interest using artificial Intelligence (AI) to assist this process. AI introduces limitless possibilities future diagnosis AD, yet still resistance from healthcare community incorporate clinical setting. The goal review answer question whether should be used conjunction with AD. To question, possible benefits disadvantages are discussed. main advantages its potential improve accuracy, efficiency radiographic data, reduce physician burnout, advance precision medicine. include generalization data shortage, lack vivo gold standard, skepticism medical community, bias, concerns over patient information, privacy, safety. challenges present fundamental must addressed when time comes, it would unethical not use if can health outcome.

Language: Английский

---