A Comprehensive Review of Conventional, Machine Leaning, and Deep Learning Models for Groundwater Level (GWL) Forecasting

Applied Sciences, Год журнала: 2023, Номер 13(4), С. 2743 - 2743

Опубликована: Фев. 20, 2023

Groundwater level (GWL) refers to the depth of water table or below Earth’s surface in underground formations. It is an important factor managing and sustaining groundwater resources that are used for drinking water, irrigation, other purposes. prediction a critical aspect resource management requires accurate efficient modelling techniques. This study reviews most commonly conventional numerical, machine learning, deep learning models predicting GWL. Significant advancements have been made terms efficiency over last two decades. However, while researchers primarily focused on monthly, weekly, daily, hourly GWL, managers strategists require multi-year GWL simulations take effective steps towards ensuring sustainable supply groundwater. In this paper, we consider collection state-of-the-art theories develop design novel methodology improve field evaluation. We examined 109 research articles published from 2008 2022 investigated different Finally, concluded approaches Moreover, provide possible future directions recommendations enhance accuracy relevant understanding.

Язык: Английский

---

Application of Artificial Intelligence Techniques for Monkeypox: A Systematic Review

Diagnostics, Год журнала: 2023, Номер 13(5), С. 824 - 824

Опубликована: Фев. 21, 2023

Monkeypox or Mpox is an infectious virus predominantly found in Africa. It has spread to many countries since its latest outbreak. Symptoms such as headaches, chills, and fever are observed humans. Lumps rashes also appear on the skin (similar smallpox, measles, chickenpox). Many artificial intelligence (AI) models have been developed for accurate early diagnosis. In this work, we systematically reviewed recent studies that used AI mpox-related research. After a literature search, 34 fulfilling prespecified criteria were selected with following subject categories: diagnostic testing of mpox, epidemiological modeling mpox infection spread, drug vaccine discovery, media risk management. beginning, detection using various modalities was described. Other applications ML DL mitigating categorized later. The machine deep learning algorithms their performance discussed. We believe state-of-the-art review will be valuable resource researchers data scientists developing measures counter spread.

Язык: Английский

---

Adazd-Net: Automated adaptive and explainable Alzheimer’s disease detection system using EEG signals

Knowledge-Based Systems, Год журнала: 2023, Номер 278, С. 110858 - 110858

Опубликована: Июль 29, 2023

Alzheimer's disease (AZD) is a degenerative neurological condition that causes dementia and leads the brain to atrophy. Although AZD cannot be cured, early detection prompt treatment can slow down its progression. effectively identified via electroencephalogram (EEG) signals. But, it challenging analyze EEG signals since they change quickly spontaneously. Additionally, clinicians offer very little trust existing models due lack of explainability in predictions machine learning or deep models. The paper novel Adazd-Net which an adaptive explanatory framework for automated identification using We propose flexible analytic wavelet transform, automatically adjusts changes EEGs. optimum number features needed effective system performance also explored this work, along with discovery most discriminant channel. presents technique used explain both individual overall provided by classifier model. have obtained accuracy 99.85% detecting ten-fold cross-validation strategy. suggested precise explainable technique. Researchers investigate hidden information concerning during our proposed Our developed model employed hospital scenario detect AZD, as accurate robust.

Язык: Английский

---

An Explainable Deep Learning Model to Prediction Dental Caries Using Panoramic Radiograph Images

Diagnostics, Год журнала: 2023, Номер 13(2), С. 226 - 226

Опубликована: Янв. 7, 2023

Dental caries is the most frequent dental health issue in general population. can result extreme pain or infections, lowering people’s quality of life. Applying machine learning models to automatically identify lead earlier treatment. However, physicians frequently find model results unsatisfactory due a lack explainability. Our study attempts address this with an explainable deep for detecting caries. We tested three prominent pre-trained models, EfficientNet-B0, DenseNet-121, and ResNet-50, determine which best detection task. These take panoramic images as input, producing caries–non-caries classification heat map, visualizes areas interest on tooth. The performance was evaluated using whole 562 subjects. All produced remarkably similar results. ResNet-50 exhibited slightly better when compared EfficientNet-B0 DenseNet-121. This obtained accuracy 92.00%, sensitivity 87.33%, F1-score 91.61%. Visual inspection showed us that maps were also located proposed diagnosed high reliability. help explain by indicating region suspected teeth. Dentists could use these validate reduce misclassification.

Язык: Английский

---

PatchResNet: Multiple Patch Division–Based Deep Feature Fusion Framework for Brain Tumor Classification Using MRI Images

Journal of Digital Imaging, Год журнала: 2023, Номер 36(3), С. 973 - 987

Опубликована: Фев. 16, 2023

Язык: Английский

---

Explainable Artificial Intelligence in Alzheimer’s Disease Classification: A Systematic Review

Cognitive Computation, Год журнала: 2023, Номер 16(1), С. 1 - 44

Опубликована: Ноя. 13, 2023

Abstract The unprecedented growth of computational capabilities in recent years has allowed Artificial Intelligence (AI) models to be developed for medical applications with remarkable results. However, a large number Computer Aided Diagnosis (CAD) methods powered by AI have limited acceptance and adoption the domain due typical blackbox nature these models. Therefore, facilitate among practitioners, models' predictions must explainable interpretable. emerging field (XAI) aims justify trustworthiness predictions. This work presents systematic review literature reporting Alzheimer's disease (AD) detection using XAI that were communicated during last decade. Research questions carefully formulated categorise into different conceptual approaches (e.g., Post-hoc, Ante-hoc, Model-Agnostic, Model-Specific, Global, Local etc.) frameworks (Local Interpretable Model-Agnostic Explanation or LIME, SHapley Additive exPlanations SHAP, Gradient-weighted Class Activation Mapping GradCAM, Layer-wise Relevance Propagation LRP, XAI. categorisation provides broad coverage interpretation spectrum from intrinsic Ante-hoc models) complex patterns Post-hoc taking local explanations global scope. Additionally, forms interpretations providing in-depth insight factors support clinical diagnosis AD are also discussed. Finally, limitations, needs open challenges research outlined possible prospects their usage detection.

Язык: Английский

---

Artificial Intelligence for Automatic Pain Assessment: Research Methods and Perspectives

Pain Research and Management, Год журнала: 2023, Номер 2023, С. 1 - 13

Опубликована: Июнь 28, 2023

Although proper pain evaluation is mandatory for establishing the appropriate therapy, self-reported level assessment has several limitations. Data-driven artificial intelligence (AI) methods can be employed research on automatic (APA). The goal development of objective, standardized, and generalizable instruments useful in different clinical contexts. purpose this article to discuss state art perspectives APA applications both scenarios. Principles AI functioning will addressed. For narrative purposes, AI-based are grouped into behavioral-based approaches neurophysiology-based detection methods. Since generally accompanied by spontaneous facial behaviors, based image classification feature extraction. Language features through natural language strategies, body postures, respiratory-derived elements other investigated approaches. Neurophysiology-based obtained electroencephalography, electromyography, electrodermal activity, biosignals. Recent involve multimode strategies combining behaviors with neurophysiological findings. Concerning methods, early studies were conducted machine learning algorithms such as support vector machine, decision tree, random forest classifiers. More recently, neural networks convolutional recurrent network implemented, even combination. Collaboration programs involving clinicians computer scientists must aimed at structuring processing robust datasets that used various settings, from acute chronic conditions. Finally, it crucial apply concepts explainability ethics when examining management.

Язык: Английский

---

Ethical Framework for Harnessing the Power of AI in Healthcare and Beyond

IEEE Access, Год журнала: 2024, Номер 12, С. 31014 - 31035

Опубликована: Янв. 1, 2024

In the past decade, deployment of deep learning (Artificial Intelligence (AI)) methods has become pervasive across a spectrum real-world applications, often in safety-critical contexts. This comprehensive research article rigorously investigates ethical dimensions intricately linked to rapid evolution AI technologies, with particular focus on healthcare domain. Delving deeply, it explores multitude facets including transparency, adept data management, human oversight, educational imperatives, and international collaboration within realm advancement. Central this is proposition conscientious framework, meticulously crafted accentuate values equity, answerability, human-centric orientation. The second contribution in-depth thorough discussion limitations inherent systems. It astutely identifies potential biases intricate challenges navigating multifaceted Lastly, unequivocally accentuates pressing need for globally standardized ethics principles frameworks. Simultaneously, aptly illustrates adaptability framework proposed herein, positioned skillfully surmount emergent challenges.

Язык: Английский

---

On the failings of Shapley values for explainability

International Journal of Approximate Reasoning, Год журнала: 2024, Номер 171, С. 109112 - 109112

Опубликована: Янв. 10, 2024

Язык: Английский

---

Explainable AI-driven IoMT fusion: Unravelling techniques, opportunities, and challenges with Explainable AI in healthcare

Information Fusion, Год журнала: 2024, Номер 110, С. 102472 - 102472

Опубликована: Май 16, 2024

Язык: Английский

---