Application of deep learning for fast detection of COVID-19 in X-Rays using nCOVnet

Chaos Solitons & Fractals, Journal Year: 2020, Volume and Issue: 138, P. 109944 - 109944

Published: May 27, 2020

Language: Английский

---

Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence

Cognitive Computation, Journal Year: 2023, Volume and Issue: 16(1), P. 45 - 74

Published: Aug. 24, 2023

Abstract Recent years have seen a tremendous growth in Artificial Intelligence (AI)-based methodological development broad range of domains. In this rapidly evolving field, large number methods are being reported using machine learning (ML) and Deep Learning (DL) models. Majority these models inherently complex lacks explanations the decision making process causing to be termed as 'Black-Box'. One major bottlenecks adopt such mission-critical application domains, banking, e-commerce, healthcare, public services safety, is difficulty interpreting them. Due rapid proleferation AI models, explaining their getting harder which require transparency easy predictability. Aiming collate current state-of-the-art black-box study provides comprehensive analysis explainable (XAI) To reduce false negative positive outcomes back-box finding flaws them still difficult inefficient. paper, XAI reviewed meticulously through careful selection research. It also in-depth evaluation frameworks efficacy serve starting point for applied theoretical researchers. Towards end, it highlights emerging critical issues pertaining research showcase major, model-specific trends better explanation, enhanced transparency, improved prediction accuracy.

Language: Английский

---

Deep Learning in Mining Biological Data

Cognitive Computation, Journal Year: 2021, Volume and Issue: 13(1), P. 1 - 33

Published: Jan. 1, 2021

Recent technological advancements in data acquisition tools allowed life scientists to acquire multimodal from different biological application domains. Categorized three broad types (i.e. images, signals, and sequences), these are huge amount complex nature. Mining such enormous of for pattern recognition is a big challenge requires sophisticated data-intensive machine learning techniques. Artificial neural network-based systems well known their capabilities, lately deep architectures-known as (DL)-have been successfully applied solve many problems. To investigate how DL-especially its architectures-has contributed utilized the mining pertaining those types, meta-analysis has performed resulting resources have critically analysed. Focusing on use DL analyse patterns diverse domains, this work investigates architectures' applications data. This followed by an exploration available open access sources along with popular open-source applicable Also, comparative investigations qualitative, quantitative, benchmarking perspectives provided. Finally, some research challenges using mine outlined number possible future put forward.

Language: Английский

---

A review of epileptic seizure detection using machine learning classifiers

Brain Informatics, Journal Year: 2020, Volume and Issue: 7(1)

Published: May 25, 2020

Epilepsy is a serious chronic neurological disorder, can be detected by analyzing the brain signals produced neurons. Neurons are connected to each other in complex way communicate with human organs and generate signals. The monitoring of these commonly done using Electroencephalogram (EEG) Electrocorticography (ECoG) media. These complex, noisy, non-linear, non-stationary produce high volume data. Hence, detection seizures discovery brain-related knowledge challenging task. Machine learning classifiers able classify EEG data detect along revealing relevant sensible patterns without compromising performance. As such, various researchers have developed number approaches seizure machine statistical features. main challenges selecting appropriate aim this paper present an overview wide varieties techniques over last few years based on taxonomy features classifiers-'black-box' 'non-black-box'. presented state-of-the-art methods ideas will give detailed understanding about classification, research directions future.

Language: Английский

---

Application of deep learning in detecting neurological disorders from magnetic resonance images: a survey on the detection of Alzheimer’s disease, Parkinson’s disease and schizophrenia

Brain Informatics, Journal Year: 2020, Volume and Issue: 7(1)

Published: Oct. 9, 2020

Neuroimaging, in particular magnetic resonance imaging (MRI), has been playing an important role understanding brain functionalities and its disorders during the last couple of decades. These cutting-edge MRI scans, supported by high-performance computational tools novel ML techniques, have opened up possibilities to unprecedentedly identify neurological disorders. However, similarities disease phenotypes make it very difficult detect such accurately from acquired neuroimaging data. This article critically examines compares performances existing deep learning (DL)-based methods disorders-focusing on Alzheimer's disease, Parkinson's schizophrenia-from data using different modalities including functional structural MRI. The comparative performance analysis various DL architectures across suggests that Convolutional Neural Network outperforms other detecting Towards end, a number current research challenges are indicated some possible future directions provided.

Language: Английский

---

Deep Learning Approach for Early Detection of Alzheimer’s Disease

Cognitive Computation, Journal Year: 2021, Volume and Issue: 14(5), P. 1711 - 1727

Published: Nov. 3, 2021

Language: Английский

---

Brain-Computer Interface: Advancement and Challenges

Sensors, Journal Year: 2021, Volume and Issue: 21(17), P. 5746 - 5746

Published: Aug. 26, 2021

Brain-Computer Interface (BCI) is an advanced and multidisciplinary active research domain based on neuroscience, signal processing, biomedical sensors, hardware, etc. Since the last decades, several groundbreaking has been conducted in this domain. Still, no comprehensive review that covers BCI completely yet. Hence, a overview of presented study. This study applications upholds significance Then, each element systems, including techniques, datasets, feature extraction methods, evaluation measurement matrices, existing algorithms, classifiers, are explained concisely. In addition, brief technologies or mostly sensors used BCI, appended. Finally, paper investigates unsolved challenges explains them with possible solutions.

Language: Английский

---

Security Threats and Artificial Intelligence Based Countermeasures for Internet of Things Networks: A Comprehensive Survey

IEEE Access, Journal Year: 2021, Volume and Issue: 9, P. 94668 - 94690

Published: Jan. 1, 2021

The Internet of Things (IoT) has emerged as a technology capable connecting heterogeneous nodes/objects, such people, devices, infrastructure, and makes our daily lives simpler, safer, fruitful. Being part large network these nodes are typically resource-constrained became the weakest link to cyber attacker. Classical encryption techniques have been employed ensure data security IoT network. However, high-level cannot be in devices due limitation resources. In addition, node is still challenge for engineers. Thus, we need explore complete solution networks that can security. rule-based approaches shallow deep machine learning algorithms- branches Artificial Intelligence (AI)- countermeasures along with existing protocols. This paper presented comprehensive layer-wise survey on threats, AI-based models impede threats. Finally, open challenges future research directions addressed safeguard

Language: Английский

---

Machine learning for synergistic network pharmacology: a comprehensive overview

Briefings in Bioinformatics, Journal Year: 2023, Volume and Issue: 24(3)

Published: April 6, 2023

Abstract Network pharmacology is an emerging area of systematic drug research that attempts to understand actions and interactions with multiple targets. has changed the paradigm from ‘one-target one-drug’ highly potent ‘multi-target drug’. Despite that, this synergistic approach currently facing many challenges particularly mining effective information such as targets, mechanism action, organism interaction massive, heterogeneous data. To overcome bottlenecks in multi-target discovery, computational algorithms are welcomed by scientific community. Machine learning (ML) especially its subfield deep (DL) have seen impressive advances. Techniques developed within these fields now able analyze learn huge amounts data disparate formats. In terms network pharmacology, ML can improve discovery decision making big Opportunities apply occur all stages research. Examples include screening biologically active small molecules, target identification, metabolic pathways protein–protein analysis, hub gene analysis finding binding affinity between compounds proteins. This review summarizes premier algorithmic concepts forecasts future opportunities, potential applications well several remaining implementing pharmacology. our knowledge, study provides first comprehensive assessment approaches we hope it encourages additional efforts toward development acceptance pharmaceutical industry.

Language: Английский

---

A comparative analysis of machine learning classifiers for stroke prediction: A predictive analytics approach

Healthcare Analytics, Journal Year: 2022, Volume and Issue: 2, P. 100116 - 100116

Published: Oct. 13, 2022

Stroke is the third leading cause of death in world. It a dangerous health disorder caused by interruption blood flow to brain, resulting severe illness, disability, or death. An accurate prediction stroke necessary for early stage treatment and overcoming mortality rate. This study proposes machine learning approach diagnose with imbalanced data more accurately. Random Over Sampling (ROS) technique has been used this work balance data. Eleven classifiers, including Support Vector Machine, Forest, K-nearest Neighbor, Decision Tree, Naïve Bayes, Voting Classifier, AdaBoost, Gradient Boosting, Multi-Layer Perception, Nearest Centroid, are analyzed study. Ten classifiers show than 90% results before balancing four display 96% after data-balancing using oversampling method. The Hyperparameter tuning cross-validation performed each model enhance results. Moreover, Accuracy, F1-Measure, Precision, Recall measure performance models. Machine highest accuracy 99.99%, recall values precision F1-measure 99.99%. Forest achieves second-highest 99.87%, 0.001% error. In addition, user-friendly web app mobile built based on most model.

Language: Английский

---