An XAI Based Autism Detection: The Context Behind the Detection

Biswas, Milon; Kaiser, M. Shamim; Mahmud, Mufti; Mamun, Shamim Al; Hossain, Md. Shahadat; Rahman, Muhammad Arifur

doi:10.1007/978-3-030-86993-9_40

Cited by 75 publications

(15 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Conventionally, deep learning and machine learning models are trained by contriving machine-generated intermediary feature sets, which can not be explainable by humans [39], [40], [41]. In such a case, there is a need to know human-interpretable features that underlie classification and their associative importance [42], [43], [44]. Here, we used Integrated Gradient (IG) for deep learning; we applied SHAP and LIME for machine learning models that developed an automated AI method for identifying neuro-biological features and hyper-parameters and ranked them in order of importance [45], [46], [47], [48].…”

Section: Discussionmentioning

confidence: 99%

End-to-End Explainable AI: Derived Theory-of-Mind Fingerprints to Distinguish Between Autistic and Typically developing and Social Symptom Severity

Banerjee

Roy

2023

Preprint

View full text Add to dashboard Cite

Theory-of-Mind (ToM) is an evolving ability that significantly impacts human learning and cognition. Early development of ToM ability allows one to comprehend other individuals aims and ambitions, as well as thinking that differs from own. Autism Spectrum Disorder (ASD) is the prevalent pervasive neurodevelopmental disorder in which participants brains appeared to be marked by diffuse variations throughout large-scale brain systems made up of functionally connected but physically separated brain areas that got abnormalities in willed action, self-monitoring and monitoring the intents of others, often known as ToM. Although functional neuroimaging techniques have been widely used to establish the neural correlates implicated in ToM, the specific mechanisms still need to be clarified. The availability of current Big data and Artificial Intelligence (AI) frameworks paves the way for systematically identifying Autistics from typically developing by identifying neural correlates and connectome-based features to generate accurate classifications and predictions of socio-cognitive impairment. In this work, we develop an Ex-AI model that quantifies the common sources of variability in ToM brain regions between typically developing and ASD individuals. Our results identify a feature set on which the classification model can be trained to learn characteristics differences and classify ASD and TD ToM development more distinctly. This approach can also estimate heterogeneity within ASD ToM subtypes and their association with the symptom severity scores based on socio-cognitive impairments. Based on our proposed framework, we obtain more than 90% accuracy using Explainable ML (Ex-Ml) models and an average of 96% classification accuracy using Explainable Deep Neural Network (Ex-DNN) models. Our findings identify three important sub-groups within ASD samples based on the key differences and heterogeneity in resting state ToM regions functional connectivity patterns and predictive of mild to severe atypical social cognition and communication deficits through early developmental stages.

show abstract

Section: Discussionmentioning

confidence: 99%

End-to-End Explainable AI: Derived Theory-of-Mind Fingerprints to Distinguish Between Autistic and Typically developing and Social Symptom Severity

Banerjee

Roy

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In recent years artificial intelligence (AI) has been applied in diverse problem domains to solve various challenging problems, including text classification [13,14,15,16], cyber security [17,18,19,20], neurological disease detection [21,22,23,12] and management [24,25,26,27,28,29], elderly care [30,31], fighting pandemic [32,33,34,35,36,37,38], and healthcare service delivery [39,40,41]. In particular, deep learning (DL) has attracted a lot of attention [6,7].…”

Section: Related Workmentioning

confidence: 99%

Four-Way Classification of Alzheimer's Disease using Deep Siamese Convolutional Neural Network with Triplet-Loss Function

Hajamohideen

Shaffi

Mahmud

et al. 2022

Preprint

View full text Add to dashboard Cite

Alzheimer's disease (AD) is a neurodegenerative disease that causes irreversible damage to several brain regions, including the hippocampus causing impairment in cognition, function, and behaviour. Early diagnosis of the disease will reduce the suffering of the patients and their family members. Towards this aim, in this paper, we propose a Siamese Convolutional Neural Network (CNN) architecture that employs the triplet-loss function for the representation of input MRI images as k-dimensional embeddings. We used both pre-trained and non-pre-trained CNNs to transform images into the embedding space. These embeddings are subsequently used for the 4-way classification of Alzheimer's Disease. The model efficacy was tested using the ADNI and OASIS datasets which produced an accuracy of 91.83% and 93.85%, respectively. Furthermore, obtained results are compared with similar methods proposed in the literature.

show abstract

“…DL [1][2][3][4][5][6], blockchain technology [7][8][9][10][11][12][13][14][15][16], along with big data technology [17][18][19][20][21][22][23][24][25] and highperformance computing [26] has created new opportunities for revealing, quantifying, and understanding data-intensive workflows in agricultural operating contexts. Among other definitions, DL is defined as the field of science that empowers ML and it is also used in more and more scientific fields year after year, such as bioinformatics [27][28][29][30], biochemistry [31], medicine [32], meteorology [33], economics [34], robotics [35][36][37][38], aquaculture [39], food safety [40][41][42][43] and climatology [44].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning in Agriculture: A Review

Bharman

Saad

Khan

et al. 2022

AJRCoS

View full text Add to dashboard Cite

Deep learning (DL) is a kind of sophisticated data analysis and image processing technology, with good results and great potential. DL has been applied to many different fields, and it is also being applied to the agricultural field. This paper presents a wide-ranging review of research with regards to how DL is applied to agriculture. The analyzed works were categorized in yield prediction, weed detection, and disease detection. The articles presented here illustrate the benefits of DL to agriculture through filtering and categorization. Farm management systems are turning into real-time AI-enabled applications that give in-depth insights and suggestions for farmer's decision support by using the proper utilization of DL and sensor data.

show abstract

An XAI Based Autism Detection: The Context Behind the Detection

Cited by 75 publications

References 26 publications

End-to-End Explainable AI: Derived Theory-of-Mind Fingerprints to Distinguish Between Autistic and Typically developing and Social Symptom Severity

End-to-End Explainable AI: Derived Theory-of-Mind Fingerprints to Distinguish Between Autistic and Typically developing and Social Symptom Severity

Four-Way Classification of Alzheimer's Disease using Deep Siamese Convolutional Neural Network with Triplet-Loss Function

Deep Learning in Agriculture: A Review

Contact Info

Product

Resources

About