Computational Intelligent Models for Alzheimer's Prediction Using Audio Transcript Data

Khan, Yusera Farooq; Kaushik, Baijnath; Mir, Bilal Ahmed

doi:10.31577/cai_2022_6_1589

Cited by 4 publications

(1 citation statement)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The outcomes show that the suggested approach beats cutting-edge algorithms in accuracy and loss [40].…”

Section: Results Evaluationmentioning

confidence: 91%

WITHDRAWN: HHO-UNet-IAA: Harris Hawks Optimization based Novel UNet-Inception Attention Architecture for Glaucoma Segmentation

khan,

Banerjee,

Narula

et al. 2024

Preprint

View full text Add to dashboard Cite

An accurate diagnosis is significant in preventing blindness because ophthalmology is one of the most prevalent causes of blindness worldwide. Glaucoma is diagnosed with a scanning-laser-tomography examination of the optic nerve head. The surface topography of the optic nerve head is captured and analyzed by this technique. The manual delineation of the optic nerve head by a skilled ophthalmologist is required for the analysis that results in a diagnosis of the illness. Transfer learning based computerized glaucoma classification has achieved effective outcomes. This study presents and validates a novel heuristic-based UNet-Inception attention framework for glaucoma optic nerve segmentation and classification. The suggested technique is based on the concept of merging the benefits of two distinct networks, such as the UNet and Inception framework for automatic segmentation of Glaucoma, along with the blend of the Harris Hawks approach for selecting impact features and a hybrid loss function. Using a database of fundus images, the proposed design was evaluated and compared to several state-of-the-art methods. The integration of the UNet-Inception architecture with the Haris Hawk Optimisation technique in the field of ophthalmology image segmentation has shown potential for substantial enhancements in terms of accuracy, efficiency, and adaptability based on the performance evaluation of this study. Using their combined abilities, these components proposed an efficient, automated ophthalmic classification framework. The fitness evaluation based on Intersection over Union (IoU) indicates that the model's performance is in accordance with the segmentation task. With a median DSC of 0.9892 for the optical nerve head (ONH) segments and 0.98718 for delineating the optic nerve head layer (RNFL), the findings show that the suggested technique performs better than the other techniques in terms of segmented images.

show abstract

“…The outcomes show that the suggested approach beats cutting-edge algorithms in accuracy and loss [40].…”

Section: Results Evaluationmentioning

confidence: 91%

WITHDRAWN: HHO-UNet-IAA: Harris Hawks Optimization based Novel UNet-Inception Attention Architecture for Glaucoma Segmentation

khan,

Banerjee,

Narula

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Uncovering Linguistic Patterns: A Machine Learning Exploration for Early Dementia Detection in Speech Transcripts

Shakeri,

Freja,

Hallaj

et al. 2024

2024 4th International Conference on Applied Artificial Intelligence (ICAPAI)

View full text Add to dashboard Cite

Early diagnosis of Alzheimer’s Disease based on multi-attention mechanism

Yang,

Hong,

Zhang

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Alzheimer’s Disease is a neurodegenerative disorder, and one of its common and prominent early symptoms is language impairment. Therefore, early diagnosis of Alzheimer’s Disease through speech and text information is of significant importance. However, the multimodal data is often complex and inconsistent, which leads to inadequate feature extraction. To address the problem, We propose a model for early diagnosis of Alzheimer’s Disease based on multimodal attention(EDAMM). Specifically, we first evaluate and select three optimal feature extraction methods, Wav2Vec2.0, TF-IDF and Word2Vec, to extract acoustic and linguistic features. Next, by leveraging self-attention mechanism and cross-modal attention mechanisms, we generate fused features to enhance and capture the inter-modal correlation information. Finally, we concatenate the multimodal features into a composite feature vector and employ a Neural Network(NN) classifier to diagnose Alzheimer’s Disease. To evaluate EDAMM, we perform experiments on two public datasets, i.e., NCMMSC2021 and ADReSSo. The results show that EDAMM improves the performance of Alzheimer’s Disease diagnosis over state-of-the-art baseline approaches on both datasets.

show abstract

Computational Intelligent Models for Alzheimer's Prediction Using Audio Transcript Data

Cited by 4 publications

References 44 publications

WITHDRAWN: HHO-UNet-IAA: Harris Hawks Optimization based Novel UNet-Inception Attention Architecture for Glaucoma Segmentation

WITHDRAWN: HHO-UNet-IAA: Harris Hawks Optimization based Novel UNet-Inception Attention Architecture for Glaucoma Segmentation

Uncovering Linguistic Patterns: A Machine Learning Exploration for Early Dementia Detection in Speech Transcripts

Early diagnosis of Alzheimer’s Disease based on multi-attention mechanism

Contact Info

Product

Resources

About