Paper
Neural memory plasticity for medical anomaly detection
Published Apr 18, 2020 · Tharindu Fernando, Simon Denman, David Ahmedt-Aristizabal
Neural networks : the official journal of the International Neural Network Society
Q1 SJR score
34
Citations
0
Influential Citations
Abstract
Abstract removed due to Elsevier request; this does not indicate any issues with the research. Click the full text link above to read the abstract and view the original source.
Study Snapshot
Key takeawayThe proposed neural memory access mechanism, combining static and dynamic connection weights, outperforms current state-of-the-art in medical anomaly detection tasks like abnormal EEG identification, MRI tumor type classification, and schizophrenia risk detection in children.
PopulationOlder adults (50-71 years)
Sample size24
MethodsObservational
OutcomesBody Mass Index projections
ResultsSocial networks mitigate obesity in older groups.
Sign up to use Study Snapshot
Consensus is limited without an account. Create an account or sign in to get more searches and use the Study Snapshot.
Full text analysis coming soon...
References
A Survey of Adaptive Resonance Theory Neural Network Models for Engineering Applications
This survey surveys adaptive resonance theory neural network models for engineering applications, examining their speed, configurability, explainability, parallelization, and hardware implementation, with a focus on engineering properties and challenges.
2019·60citations·Leonardo Enzo Brito da Silva et al.·Neural networks : the official journal of the International Neural Network Society
Neural networks : the official journal of the International Neural Network Society
Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection
MemAE, an improved deep autoencoder, effectively detects anomalies by reconstructed errors being close to normal data, reducing miss detection.
2019·1082citations·Dong Gong et al.·2019 IEEE/CVF International Conference on Computer Vision (ICCV)
2019 IEEE/CVF International Conference on Computer Vision (ICCV)
A Hybrid Feature Extraction Method With Regularized Extreme Learning Machine for Brain Tumor Classification
The hybrid feature extraction method with regularized extreme learning machine (RELM) improves brain tumor classification accuracy compared to existing state-of-the-art approaches.
2019·270citations·Abdu H. Gumaei et al.·IEEE Access
IEEE Access
Multi-grade brain tumor classification using deep CNN with extensive data augmentation
Our deep CNN-based multi-grade brain tumor classification system effectively classifies tumors using MRI data, outperforming existing methods.
2019·591citations·M. Sajjad et al.·J. Comput. Sci.
J. Comput. Sci.
A deep convolutional neural network model for automated identification of abnormal EEG signals
The proposed 1D CNN model accurately classifies normal and abnormal EEG signals with a classification error rate of 20.66%, aiding clinicians in accurate diagnosis of health conditions.
2018·153citations·Özal Yildirim et al.·Neural Computing and Applications
Neural Computing and Applications
Citations
DETECTION OF ORAL SQUAMOUS CELL CARCINOMA USING PRE-TRAINED DEEP LEARNING MODELS.
Transfer learning-based methodologies using pre-trained deep learning models and convolutional neural networks show potential for improving early diagnosis of oral squamous cell carcinoma.
2024·0citations·K. Dhanya et al.·Experimental oncology
Experimental oncology
Model-Based Approaches to Investigating Mismatch Responses in Schizophrenia.
Model-based approaches can provide valuable insights into the disruptions of neural mechanisms and cognitive function in schizophrenia.
2024·0citations·Dirk C Gütlin et al.·Clinical EEG and neuroscience
Clinical EEG and neuroscience
Spatiotemporal Masked Autoencoder with Multi-Memory and Skip Connections for Video Anomaly Detection
The SMAMS model, combining spatiotemporal masked autoencoder and memory modules, improves video anomaly detection by utilizing high-level semantic and temporal contextual information.
2024·8citations·Yan Fu et al.·Electronics
Electronics
Empirical Analysis of Anomaly Detection on Hyperspectral Imaging Using Dimension Reduction Methods
Feature selection in hyperspectral imaging is 6.90x faster for anomaly detection compared to feature extraction-based approaches, maintaining detection performance.
2024·0citations·Dongeon Kim et al.·ArXiv
ArXiv
Hard Anomaly Detection: An Adversarial Data Augmentation Solution
The HAD framework, using a GAN-based method called HadGAN, effectively detects hard anomalies with unobvious boundaries and imbalanced distributions, outperforming regular classifiers.
2023·0citations·Hu Teng et al.·2023 IEEE International Conference on Data Mining Workshops (ICDMW)
2023 IEEE International Conference on Data Mining Workshops (ICDMW)
Multilevel Saliency-Guided Self-Supervised Learning for Image Anomaly Detection
CutSwap, a multilevel saliency-guided self-supervised learning method, generates more subtle yet realistic negative samples for image anomaly detection, achieving state-of-the-art performance on mainstream benchmark datasets.
2023·0citations·Jianjian Qin et al.·Signal Image Video Process.
Signal Image Video Process.
Efficient-YOLOv8: Multi-Scale ConvNet for Underwater Object Detection
Efficient-YOLOv8 is a novel underwater object detection framework that achieves remarkable results, particularly in cuttlefish detection, with a precision of 94.18%, recall of 97.40%, and mAP of 98.18%.
2023·0citations·Lin Xu et al.·Proceedings of the 8th International Conference on Sustainable Information Engineering and Technology
Proceedings of the 8th International Conference on Sustainable Information Engineering and Technology