Neurology India
menu-bar5 Open access journal indexed with Index Medicus
  Users online: 5107  
 Home | Login 
About Editorial board Articlesmenu-bullet NSI Publicationsmenu-bullet Search Instructions Online Submission Subscribe Videos Etcetera Contact
  Navigate Here 
 Resource Links
  »  Similar in PUBMED
 »  Search Pubmed for
 »  Search in Google Scholar for
 »Related articles
  »  Article in PDF (2,133 KB)
  »  Citation Manager
  »  Access Statistics
  »  Reader Comments
  »  Email Alert *
  »  Add to My List *
* Registration required (free)  

  In this Article
 »  Abstract
 » Methods
 » Results
 » Discussion
 » Conclusion
 »  References
 »  Article Figures
 »  Article Tables

 Article Access Statistics
    PDF Downloaded26    
    Comments [Add]    

Recommend this journal


Table of Contents    
Year : 2021  |  Volume : 69  |  Issue : 1  |  Page : 66-74

Deep Neural Network-based Handheld Diagnosis System for Autism Spectrum Disorder

1 I.K.G. Punjab Technical University, Kapurthala; CT Institute of Engineering, Management and Technology, Jalandhar, Punjab, India
2 I.K.G. Punjab Technical University, Kapurthala; Khalsa College of Engineering and Technology, Amritsar, Punjab, India

Date of Submission26-Dec-2017
Date of Decision08-Aug-2019
Date of Acceptance29-Oct-2019
Date of Web Publication24-Feb-2021

Correspondence Address:
Vikas Khullar
CT Institute of Engineering, Management and Technology, Jalandhar, Punjab
Login to access the Email id

Source of Support: None, Conflict of Interest: None

DOI: 10.4103/0028-3886.310069

Rights and Permissions

 » Abstract 

Objective: The aim of the present work was to propose and implement deep neural network (DNN)-based handheld diagnosis system for more accurate diagnosis and severity assessment of individuals with autism spectrum disorder (ASD).
Methods: Initially, the learning of the proposed system for ASD diagnosis was performed by implementing DNN algorithms such as a convolutional neural network (CNN) and long short-term memory (LSTM), and multilayer perceptron (MLP) with DSM-V based acquired dataset. The performance of the DNN algorithms was analyzed based on parameters viz. accuracy, loss, mean squared error (MSE), precision, recall, and area under the curve (AUC) during the training and validation process. Later, the optimum DNN algorithm, among the tested algorithms, was implemented on handheld diagnosis system (HDS) and the performance of HDS was analyzed. The stability of proposed DNN-based HDS was validated with the dataset group of 20 ASD and 20 typically developed (TD) individuals.
Results: It was observed during comparative analysis that LSTM resulted better in ASD diagnosis as compared to other artificial intelligence (AI) algorithms such as CNN and MLP since LSTM showed stabilized results achieving maximum accuracy in less consumption of epochs with minimum MSE and loss. Further, the LSTM based proposed HDS for ASD achieved optimum results with 100% accuracy in reference to DSM-V, which was validated statistically using a group of ASD and TD individuals.
Conclusion: The use of advanced AI algorithms could play an important role in the diagnosis of ASD in today's era. Since the proposed LSTM based HDS for ASD and determination of its severity provided accurate results with maximum accuracy with reference to DSM-V criteria, the proposed HDS could be the best alternative to the manual diagnosis system for diagnosis of ASD.

Keywords: Advanced artificial intelligence, ASD, deep learning, diagnosis, expert system
Key Message: Deep learning based automated handheld system with high accuracy has proposed for diagnosis of individuals with Autism Spectrum Disorder.

How to cite this article:
Khullar V, Singh HP, Bala M. Deep Neural Network-based Handheld Diagnosis System for Autism Spectrum Disorder. Neurol India 2021;69:66-74

How to cite this URL:
Khullar V, Singh HP, Bala M. Deep Neural Network-based Handheld Diagnosis System for Autism Spectrum Disorder. Neurol India [serial online] 2021 [cited 2021 Jun 18];69:66-74. Available from:

In the area of psychosis, autism spectrum disorder (ASD) is a complex developmental disorder that includes deficits associated with social interaction, communication, and repetitive or stereotypical behavior. Initially, the prevalence associated with autism was in the range of 3.3 to 16 per 10,000[1] where intermediate prevalence studies identified 60 autism cases per 10000.[2] It was evidenced that the ASD cases could be constantly increasing day-by-day[1],[3],[4] and the dramatic increase (from 4–5 in 10000 to 1 in 59) was recorded in autistic cases in various geographical locations across the world.[5–11] According to the recent report presented by Autism and Developmental Disabilities Monitoring Network in America, the percentage of ASD affected children was 1 in 59.[12] However, as per the statistics provided by the Rehabilitation Council of India, the prevalence rate in India can be 1 in 500 people or more than 2,160,000 people. The short awareness of autism diagnosis in India is a significant cause of the low prevalence rate in India. The early and correct detection of autism is participating crucially in the treatment.[13]

ASD included some significant deficits associated with social interaction, communication, and repetitive or stereotypical behavior. Typical or typically developing children usually behaved as socially interactive, gazing at faces, respond to voices, replying gestures, the immediate reaction of events, attached to caregivers, involved normal in physical activities, attracted to social activities, etc.[14],[15],[16] However, in the case of ASD, children could have atypical behavioral characteristics such as socially inactive, slow motor skills, the deficit in formal or informal language, and repetitively/stereotypical actions, or communications. The detailed symptoms of autism included lack of eye contact, lack of social responses, no attachment to caregivers, delayed motor skills, inadequate response to calling, failure to respond gestures, language delay, unusual physical control, unusual coordination, unusual attachment for objects, lack of imaginative, or pretend play, not interested in playing with other children, absence of nonverbal communication, anxious behavior, repetitive responses and so on.[17],[18],[19],[20],[21],[22],[23]

The early and accurate diagnosis of autism could help in converting the abnormal emotional behavior into survivable emotions of individuals with ASD.[24] The aim of this work was to propose the deep neural network (DNN) algorithms based handheld diagnosis system (HDS) for the correct and accurate diagnosis of ASD and identification of its severity level based on detailed DSM-V criteria.[17] The present work could be treated as an extension of the work presented by Khullar et al.[25] as the comparative analysis of the various DNN algorithms for HDS was performed on the basis of performance parameters such as accuracy, loss, mean squared error (MSE), precision, recall, and AUC.[25],[26],[27],[28],[29]

Related work

The significance of initial screening could be critical to conduct the detailed diagnostic procedure to ascertain the concrete and concerned information. Without screening tools and diagnostic criteria, it could be complicated to differentiate between different psychoses issues by nonprofessionals. The diagnosis of ASD using manual tools could depend on the capability of a physician or clinician, where accuracy could be challenged.[30] The requirement of professional ASD screening and diagnostic tools could be a high and basic need for identifying the signs and symptoms through behavioral observations and assessment questionnaires or tests.[25] Various questionnaires and interview tests for diagnosis of ASD were developed based on diagnostic and statistical manual of mental disorders, fourth and fifth edition.[17],[18] The various descriptive diagnosis tools were developed and considered in practice such as the childhood autism rating scale (CARS), modified checklist for autism in toddlers, revised with follow-up (MCHAT-R) and so on.[31],[32],[33],[34],[35]

In ASD, the correct diagnosis and identification of the disorder related symptoms could be the responsibility of the practitioner to initialize proper treatment. Now, pre-tested artificial intelligent computing techniques could perform diagnosis-related activities without human-initiated errors. With the everyday enhancement in technologies (such as virtual reality, responsive displays, wearable devices, artificial intelligence, internet of things, robotics, etc), automated behavior recognition of exceptional children and identification of causes opened several cards in the area of ASD. To achieve more accurate results in the diagnosis of certain mental disorders, advanced AI-based Computer-Aided Diagnosis (CAD) systems were used for the assistance of clinicians to diagnose different mental disorders which could be able to provide more consistent and accurate results than direct human evaluation with less time.[36],[37]

Sunsirikul et al.[38] classified ASD individuals on the basis of behavioral factors and patterns using predefined classification based association (CBA) rules. Further, multimodel behavior-related information of ASD was gathered using a socially assistive robotic system designed by Petric et al.[39] and improved objective diagnosis for ASD was developed for a repetitive, consistent, and unbiased evaluation.

Cohen et al.[40],[41] proposed the backpropagation ANN algorithm for the prediction of autism with an accuracy of 90%. Yekta et al.[28] designed an expert system for screening autism on the basis of support vector machine (SVM) and random forest (RF) algorithms and achieved accuracy of 92.4% and 93.1%, respectively. Khullar et al.[25] worked for diagnosis and identification of severity level of ASD individuals using basic artificial neural network (ANN) in which approximately optimum accuracy was achieved at 125 epochs of training with DSM-V based dataset of 128 entries. The state-of-the-art results in the area of natural language processing, handwriting identification, digital signal processing, and so on were identified by using CNN and LSTM algorithms.[42],[43],[44],[45],[46]

Alhagry et al.[46] worked for EEG signal analysis for emotion recognition using LSTM, and with an advanced artificial LSTM algorithm, 87.99% of average accuracy was achieved. AI algorithms such as a convolutional neural network (CNN) were also used for identification of subject independent smile and satisfactory accuracy of 93% was obtained.[47],[48] With the advancement in deep learning algorithms, more accurate and robust facial emotion detection systems were designed, which satisfied the user's need successfully.[49],[50] LSTM algorithm was also applied to detect suicidal ideation on different data sources and achieved accuracy in 95% during training and 88% during testing.[51]

 » Methods Top

Ethics statement

During the design and implementation of this study, a number of ethical considerations were incorporated likewise informed written consent, right to withdraw for the participants from the study at any time; none of the participants had received any psychoactive medication and anonymity of participants.

Data acquisition and participants

In this study, DSM-V Diagnostic criteria for Autism Spectrum Disorder-299.00[17] were included for the collection and creation of the ASD dataset for the training of the proposed DNN based system using the method provided by Khullar et al.[25] Initially, binary represented data of 128 entries was collected according to the format mentioned in [Table 1] where false value was represented by zero (0) and one (1) representing the true value. The outcome was also represented in the last column as ASD or Non-ASD identification remarks.
Table 1: DSM-V based Binary Data Set Format for ASD[25]

Click here to view

Further, the validation of the proposed system was conducted on the basis of collected data from 40 voluntarily participated caregivers of individuals. Of the two groups of individuals who participated, 20 children were diagnosed as ASD according to DSM-V criteria and another 20 were TD children. All the participants had normal or corrected to normal vision. [Table 2] presented the demographic characteristics of participated groups.[25]
Table 2: Demographic Characteristics of ASD and TD Individuals[25]

Click here to view

Severity level in ASD

DSM-V for ASD explained the impairments and behavior severity in three different levels as discussed below[17]:

Level 1: The patient could have a milder level of the deficit with noticeable impairments, required support for social interaction and communication and faces difficulty in the interaction, activities switching and behavioral flexibility.

Level 2: Patients required substantial support, having inflexible behavior, change nonacceptance and frequent restricted/repetitive behavior. Reduced and abnormal responses of social interactions, narrow special interests, and odd nonverbal communication reflected with limited initiation.

Level 3: The patient could have been functioning severe impairments, very low social initiation, and lack of responses caused by deficits in verbal and nonverbal communication skills. Level 3 ASD individuals could have extreme difficulty in change acceptance along with restricted/repeated behavior.

DNN algorithms

The DNN was able to overcome the hurdle in medical diagnosis with its powerful statistical paradigm in recognition of complex behavioral patterns and the ability to maintain high levels of accuracy. The various DNN algorithms such as MLP, 1-dimensional CNN, and LSTM were utilized for the analysis of acquired data and detection of ASD and further, the results were compared for the optimum performance.

Multilayer perceptron

The basic multilayer perceptron (MLP) was a traditional and common type of artificial neural network with an input layer, an output layer, and one hidden layer as shown in [Figure 1].[40],[52] In MLP, backpropagation based supervised learning and a linear sigmoid activation function were applied on each artificial neuron as.
Figure 1: Multilayer Perceptron Artificial Neural Network with Single Hidden Layer[40],[52]

Click here to view

1-Dimensional convolutional neural network

One-dimensional CNN (1D CNN) was one of the most common types of deep-multilayer perceptron (deep-MLP) models with a special structure. Every single neuron in the deep-MLP could have an activation function with more than one hidden layer in the network and an activation function mapped the weighted inputs to the output that created a special structure on CNN. The CNN architecture consisted of three basic layers such as the convolutional layer, pooling layer, and fully-connected layer, which was further connected by a rectified linear activation function for generating output as shown in [Figure 2].[53],[54],[55],[56],[57],[58],[59] Each convolution layer was convoluted with their respective kernel (filter) size as
Figure 2: Example One.Dimensional Convolutional Neural Network

Click here to view

Where y is signal, f is a filter, N number of the signals and x is output vectors respectively.

The function of max-pooling operation was to apply the reduced size feature maps after every convolution layer and also called down-sampling layer. The leaky rectified linear unit (Leaky ReLU) was used as an activation function for initial activation layers. It added nonlinearity and sparsity in the structure of the network. Softmax function was used to separate output and provided a prediction for each class. The fully connected layer contains the full connections for all activations.

The Leaky ReLU function was presented as:

The Softmax function was presented as:

Long Short-Term Memory (LSTM)

Recurrent neural networks (RNN) worked with loops in them and allowed information to persist. LSTM was the part of deep learning algorithms and a special type of RNN with essential memory cells.[60],[61] LSTM model was capable to remember information over a long period and also deal with the vanishing/exploding gradient problem that was raised during backpropagation in deep artificial neural networks. The chain-like structure of LSTM along with memory cell was shown in [Figure 3]. To add or delete the information in LSTM, the sigmoid activation function (σ) and pointwise multiplication operation (*) gates were formed.
Figure 3: LSTM Cells and their Connectivity[60],[61]

Click here to view

The standard symbols and equations for LSTM are as follows:

Xt is input vector, Ht-1 is previous (cell) output, Ct-1 is previous (cell) memory, Ht is present (cell) output, Ctis present (cell) memory, Ht + 1is next (cell) output, Ct + 1 is next (cell) memory, W and V are weight vector, σ is sigmoid function, tanh is tangent function. * is element wise multiplication function, + is represents element wise addition function.

Handheld device

Raspberry Pi with a 7-inch touch screen as shown in [Figure 4] was utilized to implement the proposed DNN-based handheld ASD diagnosis system using efficient Python programming language.[62],[63] In addition, the designed interactive graphical user interface for easy access by caregivers or clinicians was presented in [Figure 5]. The severity level of ASD individuals could be decided by the system based on integer entered such as low as integer 1, medium as integer 2, and high as integer 3.
Figure 4: Raspberry Pi with Touch Screen

Click here to view
Figure 5: Graphical User Interface of HDS

Click here to view

HDS implementation detail

The overall implementation procedure for the proposed HDS for ASD diagnosis performed through three stages such as data acquisition, training-testing of optimum algorithm among MLP, CNN, and LSTM, and further implementation and analysis of optimum DNN algorithm on HDS for individuals with ASD. The overall HDS implementation was demonstrated through the flow chart presented in [Figure 6].
Figure 6: Overall Implementation Flow of DNN-based HDS

Click here to view

Further Stepwise detail of the overall implementation of DNN based proposed HDS is as follows:

Step 1: Initially DSM-V based dataset has acquired

Step 2: Training, testing, and analysis of DNN algorithms such as MLP, CNN, and LSTM for ASD diagnosis based on parameters viz. accuracy, MSE, and loss to find an optimum and best suitable algorithm for implementation on HDS.

Step 3: Implementation of the trained model of optimum algorithm found in Step 2 on Raspberry Pi based HDS.

Step 4: Testing and analysis of optimum DNN based proposed HDS for ASD and TD subjects

Step 6: Statistical validation of the accuracy of cases with t-test

Step 7: Identification of ASD severity level.

 » Results Top

This section provided a detailed analysis of the obtained results in three cases regarding training and testing of DNN (MLP, CNN, and LSTM) algorithms, 5-fold validation and analysis of optimum DNN-based handheld diagnosis system and statistical analysis of the implemented results of case 1 and case 2.

Case 1: Training and testing of DNN algorithms - MLP, CNN, and LSTM

In this case, the MLP, CNN, and LSTM algorithm was trained and tested to find the most appropriate and accurate model with least MSE and loss. The testing was conducted by providing the different number of epochs (1 to 150) on the same training and testing data set as shown in [Table 3], [Table 4], [Table 5]. Dataset of 128 binary (0/1) entries was utilized for training and testing. The analysis was conducted based on parameters such as viz., accuracy, mean squared error, and loss as presented in [Figure 7]. The results predicted that the LSTM provided 100% accuracy at a very less number of epochs (50 epochs) as compared to CNN and MLP. It was observed from [Figure 7] that LSTM had achieved 0.02 mean square error and loss at near 50 epochs, which was very low in comparison to MLP and could not affect the results. It was observed that the LSTM algorithm provided best results among all the tested algorithms and best suitable for implementation on proposed Raspberry Pi-based HDS system.
Table 3: Number of Epoch's vs. Training and Testing Accuracy in MLP, CNN, LSTM

Click here to view
Table 4: Number of Epoch's vs. Training and Testing Loss in MLP, CNN, LSTM

Click here to view
Table 5: Number of Epoch's vs. Training and Testing MSE in MLP, CNN, LSTM

Click here to view
Figure 7: Number of Epoch's vs. Training and Testing Accuracy, Loss, and MSE in MLP, CNN, LSTM

Click here to view

Case 2: 5-fold validation and analysis of optimum DNN (LSTM) based HDS

The trained LSTM model was implemented on Raspberry Pi-based proposed HDS and the proposed handheld diagnosis system was utilized for individuals with ASD. The proposed AI-based HDS was tested with data collected from 20 ASD and 20 TD individuals according to the format presented in [Table 6]. The performance of pretrained HDS for detection of ASD was evaluated through K-fold (5-fold) analysis based on the parameters such as viz., accuracy, mean squared error, loss, precision, recall, and AUC as presented in [Figure 8], [Figure 9], [Figure 10] and [Table 6].
Table 6: Number of Epoch's vs. Validation Accuracy, MSE, Loss of LSTM based HDS

Click here to view
Figure 8: Number of Epoch's vs. Validation Accuracy of LSTM based HDS

Click here to view
Figure 9: Number of Epoch's vs. Validation MSE and Loss of LSTM based HD

Click here to view
Figure 10: Number of Epoch's vs. Validation Precision, Recall and AUC of LSTM based HDS

Click here to view

Case 3: Statistical analysis of the implemented results

The analysis of Case 1 and Case 2 was performed with the same training dataset but the testing was performed with different datasets and accuracies Acc-1 and Acc-2 were achieved for Case 1 and Case 2 respectively with different numbers of epochs. The various results for Acc-1 and Acc-2 for Case 1 and Case 2 were presented in [Table 7] with a different number of epochs. The statistical validation of the implementation results of both cases Case 1 and Case 2 was analyzed with a two-tailed t-test as represented in [Table 8]. The hypothesis of the study was considered as follows.
Table 7: Case 1 Accuracy (Acc-1) vs. Case 2 Accuracy (Acc-2)

Click here to view
Table 8: Statistical Analysis of Case 1 Accuracy (Acc-1) vs. Case 2 Accuracy (Acc-2)

Click here to view

Null Hypothesis- “No significant difference in accuracies achieved from Case-1 and Case-2”

Alternate Hypothesis- “Significant difference in the accuracy percentage achieved in Case-1 and Case-2”

The mean scores of the Case 1 accuracy were found 89.06 which was very much similar to the accuracy of the Case 2 and no significant difference was found at significant value P < 0.05

It was observed from the statistical analysis that Acc-1 of LSTM in Case 1 was similar to Acc-2 of LSTM based HDS in Case 2 and the null hypothesis was accepted.

 » Discussion Top

It was observed from the results that the LSTM algorithm provided the best training results among the tested AI algorithms with maximum accuracy. The validation of LSTM based proposed HDS was analyzed in Case-2 and it was observed from [Table 6], that the proposed system achieved 100% in 50 epochs with 0.02 loss value and almost negligible MSE. Further detailed parametric analysis using precision, recall, and AUC scores resulted as highest on the scale of zero to one. The proposed system provided maximum stability since the statistical analysis of accuracies of LSTM in Case-1 and proposed LSTM based HDS system in Case -2 were similar without significant difference. On the basis of the results found in the analysis, it was suggested that the proposed system was also successfully able to identify the DSM-V based identification of ASD level of severity as high, medium, or low.

 » Conclusion Top

The accurate diagnosis of autism plays very crucially in deciding the required correct treatment for individuals with ASD and the role of an artificially intelligent diagnosis system could fulfill the need for accurate diagnosis with negligible errors in spite of manual traditional diagnosis systems.

DNN-based HDS was designed and analyzed in the present work and it was observed that the proposed HDS system resulted in 100% accurate diagnosis of ASD along with the identification of ASD severity level in reference to DSM-V, 299.0 criteria in terms of accuracy, mean square error, and loss. It was suggested that the proposed system could be the best assistant to clinicians in the diagnosis of ASD as compared to the manual/traditional diagnosis systems. In the future, advanced artificial intelligence and evolutionary algorithms would be implemented to design HDS for medical diagnosis.


We are thankful for the IKG Punjab Technical University, India and CT Group of Institutions, India for made this research possible.

Declaration of patient consent

The authors certify that they have obtained all appropriate patient consent forms. In the form, the patient (s) has/have given his/her/their consent for his/her/their images and other clinical information to be reported in the journal. The patients understand that their names and initials will not be published and due efforts will be made to conceal their identity, but anonymity cannot be guaranteed.

Financial support and sponsorship


Conflicts of interest

There are no conflicts of interest.

 » References Top

Wing L. The definition and prevalence of autism: A review. Eur Child Adolesc Psychiatry 1993;2:61-74.  Back to cited text no. 1
Tony C, Ted R, Wendy C. Is there a gender difference in false belief development? Soc Dev 2002;11:1-10.  Back to cited text no. 2
Wing L, Potter D. The epidemiology of autistic spectrum disorders: Is the prevalence rising? Ment Retard Dev Disabil Res Rev 2002;8:151-61.  Back to cited text no. 3
Baird G, Simonoff E, Pickles A, Chandler S, Loucas T, Meldrum D, et al. Prevalence of disorders of the autism spectrum in a population cohort of children in South Thames: The Special Needs and Autism Project (SNAP). Lancet 2006;368:210-5.  Back to cited text no. 4
Ratajczak H V. Theoretical aspects of autism: Causes—A review. J Immunotoxicol 2011;8:68-79.  Back to cited text no. 5
Loucas T, Charman T, Pickles A, Simonoff E, Chandler S, Meldrum D, et al. Autistic symptomatology and language ability in autism spectrum disorder and specific language impairment. J Child Psychol Psychiatry 2008;49:1184-92.  Back to cited text no. 6
Barbaresi WJ, Katusic SK, Voigt RG. Autism-A review of the state of the science for pediatric primary health care clinicians. Arch Pediatr Adolesc Med 2006;160:1167-75.  Back to cited text no. 8
Bonnet-Brilhault F. Autism: An early neurodevelopmental disorder. Arch Pediatr 2017;24:384-90.  Back to cited text no. 9
Ardhanareeswarana K, Volkmar F. Focus: Austism spectrum disorders. Medicine (Baltimore) 2015;88:3-4.  Back to cited text no. 10
Baio J, Wiggins L, Christensen DL, Maenner MJ, Daniels J, Warren Z, et al. Prevalence of autism spectrum disorder among children aged 8 years — Autism and developmental disabilities monitoring network, 11 Sites, United States, 2014. MMWR Surveill Summ 2018;67:1-23.  Back to cited text no. 11
Data & Statistics on Autism Spectrum Disorder [Internet]. Centers Dis. Control Prev. U.S.A. 2019. Available from: [Last accessed on 2019 Sep 29].  Back to cited text no. 12
Barua M, Daley TC. Autism. Rehabil. Counc. India, Gov. India, New Delhi, 2001. p. 1-35.  Back to cited text no. 13
Bentenuto A, De Falco S, Venuti P. Mother-child play: A comparison of autism spectrum disorder, down syndrome, and typical development. Front Psychol 2016;7:1-9.  Back to cited text no. 14
Must A, Phillips SM, Curtin C, Anderson SE, Maslin M, Lividini K, et al. Comparison of sedentary behaviors between children with autism spectrum disorders and typically developing children. Autism 2014;18:376-84.  Back to cited text no. 15
Rutgers AH, Van IJzendoorn MH, Bakermans-Kranenburg MJ, Swinkels SHN, Van Daalen E, Dietz C, et al. Autism, attachment and parenting: A comparison of children with autism spectrum disorder, mental retardation, language disorder, and non-clinical children. J Abnorm Child Psychol 2007;35:859-70.  Back to cited text no. 16
Diagnostic and Statistical Manual of Mental Disorders (Fifth Edition). Arlington, VA: American Psychiatric Association; 2013.  Back to cited text no. 17
Diagnostic and Statistical Manual of Mental Disorders (Fourth Edition). Washington, DC: American Psychiatric Association; 1994.  Back to cited text no. 18
Wing L, Gould J. Severe impairments of social interaction and associated abnormalities in children: Epidemiology and classification. J Autism Dev Disord 1979;9:11-29.  Back to cited text no. 19
Klin A, Jones W, Schultz R, Volkmar F. The enactive mind, or from actions to cognition: Lessons from autism. Philos Trans R Soc 2003;358:345-60.  Back to cited text no. 20
Dawson G, Meltzoff AN, Osterling J, Rinaldi J. Neuropsychological correlates of early symptoms of autism. Child Dev 2006;69:1276.  Back to cited text no. 21
Seltzer MM, Krauss MW, Shattuck PT, Orsmond G, Swe A, Lord C. The symptoms of autism spectrum disorders. J Autism Dev Disord 2003;33:565-581. [Last accessed on 2019 Sep 29].  Back to cited text no. 22
Hazen EP, Stornelli JL, O'Rourke JA, Koesterer K, McDougle CJ. Sensory symptoms in autism spectrum disorders. Harv Rev Psychiatry 2014;22:112-24.  Back to cited text no. 23
Webb SJ, Jones EJH. Early identification of autism: Early characteristics, onset of symptoms, and diagnostic stability. Infants Young Child 2009;22:100-18.  Back to cited text no. 24
Khullar V, Singh HP, Bala M. Intelligent Handheld Expert System (HES) for diagnosis of autism spectrum disorder and its severity level. ASEAN J Psychiatry 2018;19:12-26.  Back to cited text no. 25
Haldar S, Particle swarm optimization supported artificial neural network in detection of Parkinson's disease. 2016;18:24-30.  Back to cited text no. 26
Florio T, Einfeld S, Tonge B, Brereton A. Providing an independent second opinion for the diagnosis of autism using artificial intelligence over the internet. Couns Psychother Health 2009;5:232-48.  Back to cited text no. 27
Yekta SM, Mahmoudi M, Bonab GB, Bagherzadeh B, Moradi H, Pouretemad H, et al. Developing Autism Screening Expert System (ASES). In: AWER Procedia Information Technology & Computer Science. 2013. p. 1063-8.  Back to cited text no. 28
Cihak D, Fahrenkrog C, Ayres KM, Smith C. The use of video modeling via a video iPod and a system of least prompts to improve transitional behaviors for students with autism spectrum disorders in the general education classroom. J Posit Behav Interv 2010;12:103-15.  Back to cited text no. 29
Call JD. Prevention Of Autism In A Young Infant In A Well-Child Conference. J Am Acad Child Psychiatry 1963;2:451-9.  Back to cited text no. 30
DeMyer MK, Churchill DW, Pontius W, Gilkey KM. A comparison of five diagnostic systems for childhood schizophrenia and infantile autism. J Autism Child Schizophr 1971;1:175-89.  Back to cited text no. 31
Goldenberg EP. Exploring Language with Logo. 1987.  Back to cited text no. 32
Schopler E, Reichler RJ, DeVellis RF, Daly K. Toward objective classification of childhood autism: Childhood Autism Rating Scale (CARS). J Autism Dev Disord 1980;10:91-103.  Back to cited text no. 33
Krug DA, Arick J, Almond P. Behavior checklist for identifying severely handicapped individuals with high levels of autistic behavior. J Child Psychol Psychiatry 1980;21:221-9.  Back to cited text no. 34
Robins DL, Fein D, Barton M. Modified Checklist for Autism in Toddlers, Revised with Follow-Up. Http//Www Mchatscreen Com [Internet] 2009;1–25. Available from: [Last accessed on 2019 Sep 29].  Back to cited text no. 35
Azarkhish I, Raoufy MR, Gharibzadeh S. Artificial intelligence models for predicting iron deficiency anemia and iron serum level based on accessible laboratory data. J Med Syst 2012;36:2057-61.  Back to cited text no. 36
Djemal R, Alsharabi K, Ibrahim S, Alsuwailem A. EEG-Based computer aided diagnosis of autism spectrum disorder using wavelet, entropy, and ANN. Biomed Res Int 2017;2017. doi: 10.1155/2017/9816591.  Back to cited text no. 37
Sunsirikul S, Achalakul T. Associative classification mining in the behavior study of autism spectrum disorder. 2010 2nd Int Conf Comput Autom Eng The 2nd International Conference on Computer and Automation Engineering (ICCAE) 2010 2010;3:279-83.  Back to cited text no. 38
Petric F, Hrvatini K, Babic A, Malovan L, Miklic D, Kovacic Z, et al. Four tasks of a robot-assisted autism spectrum disorder diagnostic protocol: First clinical tests. Proc 4th IEEE Glob Humanit Technol Conf GHTC 2014 2014;510-7.  Back to cited text no. 39
Cohen IL, Sudhalter V, Landon-Jimenez D, Keogh M. A neural network approach to the classification of autism. J Autism Dev Disord 1993;23:443-66.  Back to cited text no. 40
Cohen IL. An artificial neural network analogue of learning in autism. Biol Psychiatry 1994;36:5-20.  Back to cited text no. 41
Lipton ZC, Kale DC, Elkan C, Wetzel R. Learning to Diagnose with LSTM Recurrent Neural Networks. 2015. p. 1-18. Available from:  Back to cited text no. 42
Sutskever I, Vinyals O, Le QV. Sequence to Sequence Learning with Neural Networks. 2014. p. 1-9. Available from: [Last accessed on 2019 Sep 29].  Back to cited text no. 43
Karpathy A, Fei-Fei L. Deep visual-semantic alignments for generating image descriptions Andrej. IEEE Trans Pattern Anal Mach Intell 2017;39:664-76.  Back to cited text no. 44
Learn M, Discov K. Machine learning and knowledge discovery in databases. Learn Knowl Discov Databases 2014;8726:225-39.  Back to cited text no. 45
Alhagry S, Fahmy AA, El-Khoribi RA. Emotion recognition based on EEG using LSTM recurrent neural network. Int J Adv Comput Sci Appl 2017;8:8-11.  Back to cited text no. 46
Matsugu M, Mori K, Mitari Y, Kaneda Y. Subject independent facial expression recognition with robust face detection using a convolutional neural network. Neural Netw 2003;16:555-9.  Back to cited text no. 47
Chen J, Ou Q, Chi Z, Fu H. Smile detection in the wild with deep convolutional neural networks. Mach Vis Appl 2017;28:173-83.  Back to cited text no. 48
Bianco S, Celona L, Schettini R. Robust smile detection using convolutional neural networks networks. J Electron Imaging 2016;25. doi: 10.1117/1.JEI.25.6.063002.  Back to cited text no. 49
Lee S, Min C, Labs NB, Montanari A, Labs NB. Automatic smile and frown recognition with kinetic earables. In: AH2019, Reims, France. 2019.  Back to cited text no. 50
Peis I, M Olmos P, Vera-Varela C, Barrigon ML, Courtet P, Baca-Garcia E, et al. Deep sequential models for suicidal ideation from multiple source data. IEEE J Biomed Health Inform 2019. doi: 10.1109/JBHI.2019.2919270.  Back to cited text no. 51
Kononenko I. Machine learning for medical diagnosis: History, state of the art and perspective. Artif Intell Med 2001;23:89-109.  Back to cited text no. 52
Malek S, Melgani F, Bazi Y. One-dimensional convolutional neural networks for spectroscopic signal regression. J Chemom 2018;32:1-17.  Back to cited text no. 53
Hasegawa C, Iyatomi H. One-dimensional convolutional neural networks for Android malware detection. In: International Colloquium on Signal Processing & its Applications. 2018. p. 99-102.  Back to cited text no. 54
Lee S, Odom SL, Loftin R. Social engagement with peers and stereotypic behavior of children with autism. J Posit Behav Interv 2007;9:67-79.  Back to cited text no. 55
Lee SH, Maenner MJ, Heilig CM. A Comparison of Machine Learning Algorithms for the Surveillance of Autism Spectrum Disorder [Internet]. 2018. p. 1-14. Available from: [Last accessed on 2019 Sep 29].  Back to cited text no. 56
Patnam VSP, George FT, George K, Verma A. Deep Learning Based Recognition of Meltdown in Autistic Kids [Internet]. In: 2017 IEEE International Conference on Healthcare Informatics (ICHI). Park City, UT, USA: IEEE; 2017. p. 391-6. Available from: [Last accessed on 2019 Sep 29].  Back to cited text no. 57
Neubauer C. Evaluation of convolutional neural networks for visual recognition. IEEE Trans Neural Netw 1998;9:685-96.  Back to cited text no. 58
Acharya UR, Oh SL, Hagiwara Y, Tan JH, Adeli H. Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. Comput Biol Med 2018;100:270-8.  Back to cited text no. 59
Hochreiter S, Jurgen S. Long Short-Term Memory. 1997;1780:1735-80.  Back to cited text no. 60
Riva M, Amin-Hanjani S, Giussani C, De Witte O, Bruneau M. Indocyanine green videoangiography in aneurysm surgery: Systematic review and meta-analysis. Neurosurgery 2018;83:166-80.  Back to cited text no. 61
Jain S, Vaibhav A, Goyal L. Raspberry Pi based Interactive Home Automation System through E-mail. In: International Conference on Reliability, Optimization and Information Technology. 2014. p. 277-80.  Back to cited text no. 62
DATASHEET Raspberry Pi Compute Module 3+RaspberryPi Compute Module 3+Lite [Internet]. 2019; (January). Available from: [Last accessed on 2019 Sep 29].  Back to cited text no. 63


  [Figure 1], [Figure 2], [Figure 3], [Figure 4], [Figure 5], [Figure 6], [Figure 7], [Figure 8], [Figure 9], [Figure 10]

  [Table 1], [Table 2], [Table 3], [Table 4], [Table 5], [Table 6], [Table 7], [Table 8]


Print this article  Email this article
Online since 20th March '04
Published by Wolters Kluwer - Medknow