Autism Spectrum Disorder Classification Using Deep Learning

In the field of medicine, with the introduction of computer systems that can collect and analyze massive amounts of data, many non-invasive diagnostic methods are being developed for a variety of conditions. In this study, our aim is to develop a non-invasive method of classifying respiratory sounds that are recorded by an electronic stethoscope and the audio recording software that uses various machine learning algorithms.In order to store respiratory sounds on a computer, we developed a cost-effective and easy-to-use electronic stethoscope that can be used with any device. Using this device, we recorded 17,930 lung sounds from 1630 subjects.We employed two types of machine learning algorithms; mel frequency cepstral coefficient (MFCC) features in a support vector machine (SVM) and spectrogram images in the convolutional neural network (CNN). Since using MFCC features with a SVM algorithm is a generally accepted classification method for audio, we utilized its results to benchmark the CNN algorithm. We prepared four data sets for each CNN and SVM algorithm to classify respiratory audio: (1) healthy versus pathological classification; (2) rale, rhonchus, and normal sound classification; (3) singular respiratory sound type classification; and (4) audio type classification with all sound types. Accuracy results of the experiments were; (1) CNN 86%, SVM 86%, (2) CNN 76%, SVM 75%, (3) CNN 80%, SVM 80%, and (4) CNN 62%, SVM 62%, respectively.As a result, we found out that spectrogram image classification with CNN algorithm works as well as the SVM algorithm, and given the large amount of data, CNN and SVM machine learning algorithms can accurately classify and pre-diagnose respiratory audio.

Mangosteen contains a substance known as Xanthone, a phytochemical compound with the distinctive red component in mangosteen that is known for its properties as an anticancer, antibacterial, and anti-inflammatory agent. Additionally, Xanthone has the potential to strengthen the immune system, promote overall health, support mental well-being, maintain microbial balance in the body, and improve joint flexibility. The mangosteen fruit is consumable when it reaches maturity, displaying a dark purplish-black color. Besides the edible part of the fruit, the peel also possesses remarkable medicinal properties. To detect whether the fruit is ripe or not, this research employs image processing techniques. The study utilizes the HSV (Hue, Saturation, and value) color space method, CNN (Convolutional Neural Network) algorithm, and SVM (Support Vector Machine) algorithm. These methods and algorithms are chosen for their relatively high accuracy levels. The dataset used in this research is obtained from mangosteen datasets available on Kaggle. The results of this study indicate that the HSV method achieved an accuracy of 86.6%, SVM achieved an accuracy of 87%, and CNN achieved an accuracy of 91.25%. From the achieved accuracies, it is evident that the CNN algorithm yields higher accuracy compared to the others.

For a commodity, in addition to its quality, its external package is also very essential. This paper briefly introduced the intelligent support vector machine (SVM) algorithm for color design of paper packaging. The features were extracted from photos of packages using scale-invariant feature transform (SIFT), and the intelligent algorithm was trained and tested using photos of paper packaging for ceramic products collected at the ceramic crafts market as a sample set. Two paper package schemes designed in this study were used for further test. The SVM algorithm was compared with the back-propagation (BP) algorithm and the convolutional neural network (CNN) algorithm. The results showed that the three intelligent algorithms could evaluate the color design of paper packages, but the SVM algorithm was more accurate than the BP and CNN algorithms in evaluating the imagery of color design, both for the samples collected in the craft market and for the paper packaging scheme designed in this paper.

With the gradual improvement of people's living standards, the production and drinking of all kinds of food is increasing. People's disease rate has increased compared with before, which leads to the increasing number of medical image processing. Traditional technology cannot meet most of the needs of medicine. At present, convolutional neural network (CNN) algorithm using chaotic recursive diagonal model has great advantages in medical image processing and has become an indispensable part of most hospitals. This paper briefly introduces the use of medical science and technology in recent years. The hybrid algorithm of CNN in chaotic recursive diagonal model is mainly used for technical research, and the application of this technology in medical image processing is analysed. The CNN algorithm is optimized by using chaotic recursive diagonal model. The results show that the chaotic recursive diagonal model can improve the structure of traditional neural network and improve the efficiency and accuracy of the original CNN algorithm. Then, the application research and comparison of medical image processing are performed according to CNN algorithm and optimized CNN algorithm. The experimental results show that the CNN algorithm optimized by chaotic recursive diagonal model can help medical image automatic processing and patient condition analysis.

This paper deals with the identification problem of defective products of door strikers installed in automobiles based on their hammering sounds. The difference of the hammering sounds between defective and acceptable products is very small and each sound signal has a unique pattern. The capabilities of conventional human sensory tests are not enough to identify such differences between these two classes. Hence it is suggested to apply deep learning algorithms (DLA) as per the versatility and feature extraction power. Usually, some kinds of pre-processing are adopted before the application of DLA in order to increase the accuracy of inspection as well as to reduce the training and the application time of DLA. In this paper, the combinations of five kinds of pre-processing techniques and three types of DLAs are applied to the actual hammering sounds inspection of door strikers. Especially in two types of DLAs, the sound data have been evaluated as images. The evaluation results show that the combination of the wavelet analysis and the Convolutional Neural Network (CNN) only attained the 100% accuracy of inspection with great response time. The wavelet analysis and the CNN are independently attain the high performances comparing with others and it is likely that they are useful in this kind of hammering sound inspections.

Low frequency sound %3C zo Hz, known as infrasound, is generated by a variety of natural and anthropogenic sources. Following an event, infrasonic waves travel through a dynamic atmosphere that can change on the order of minutes. This makes infrasound event classification a difficult problem as waveforms from the same source type can look drastically different. Event classification usually requires ground truth information from seismic or other methods. This is time consuming, inefficient, and does not allow for a classification if the event locates somewhere other than a known source, the location accuracy is poor, or ground truth from seismic data is lacking. Here we compare the performance of the state of the art for infrasound event classification, support vector machine (SVM), to the performance of a convolutional neural network (CNN), a method that has been proven in tangential fields such as seismology. For a 1-class catalog consisting of only volcanic activity and earthquake events, the 4-fold average SVM classification accuracy is 75%, while it is 74% when using a CNN. Classification accuracies from the 4-class catalog consisting of the most common infrasound events detected at the global scale are 55% and 56% for the SVM and CNN architectures, respectively. These results demonstrate that using a CNN does not increase performance for infrasound event classification. This suggests that SVM should be the preferred classification method as it is a simpler and more trustworthy architecture and can be tied to the physical properties of the waveforms. The SVM and CNN algorithms described in this paper are not yet generalizable to other infrasound event catalogs. We anticipate this study to be a starting point for the development of large and comprehensive, systematically labeled, infrasound event catalogs as such catalogs will be necessary to provide an increase in the value of deep learning on event classification.

Hoax news is a serious problem in this era. Many people are easily led by opinions made by certain people without seeing the truth or looking for existing facts. To overcome this, many researchers have conducted hoax news detection using various algorithms. In some studies, it is said that Random Forest has better performance to overcome this hoax news problem. In other studies, it is also said that CNN has the same level of performance as the Random Forest algorithm. In addition, the problem that is often found is the error in prediction due to improper preprocessing methods. Therefore, in this research, the appropriate preprocessing method is searched by using several preprocessing scenarios for the Convolutional Neural Network (CNN) and Random Forest algorithms. Therefore, in addition to finding the right preprocessing method for each algorithm, a performance comparison is also carried out on the CNN and Random Forest algorithms using a dataset of 4000 news facts from Kompas.com and 4000 hoax news from the turnback.hoax site. the results obtained in this study are random forest has an average model accuracy value of 90% and the CNN algorithm has an average model accuracy value of 60% using the same extraction method, namely TFIDF combined with Ngrams worth one or unigram

The discussion of "can machines think?" which started with the invention of the modern computer, brought along the question of "can machines design?" by researchers in the design field. These developments in information technologies have also affected the architecture. Artificial intelligence applications are encountered in many areas such as pricing estimation, energy conservation security systems of buildings, ventilation systems, user-oriented interactive design solutions, computer-aided programs used in the plan production phase and design process. When the literature on artificial intelligence applications in the architecture is reviewed, it can be seen that it generally includes shape grammars, graph theory, decision trees, constraint-based models, machine learning methods, RNN (Recursive Neural Networks), CNN (Convolutional Neural Network) and GAN (Generative Adversarial Network) algorithms. In this study, the use of artificial intelligence algorithms in architecture was examined, and an example was designed to determine the architectural structures of different periods by using CNN (Convolutional Neural Network). In the study, the open source TensorFlow library developed by Google and the Python programming language were used. Employing a statistical approach and utilizing convolutional neural networks (CNNs), a study has successfully classified the current flow patterns of buildings based on datasets comprising facades of Gothic, Modern, and Deconstructivist architectural styles. The findings demonstrate the efficacy of CNNs in accurately distinguishing the intricate details of diverse architectural styles. Recognizing elements from different periods using the CNN algorithm can examine not only individual buildings but also the relationship of buildings with their environments. It can also gain an important place in the field of conservation of the architectural discipline. The historical processes, aesthetic features and changes of protected buildings can be learned with the CNN algorithm and can guide restoration decisions. As a result of the study, the employed CNN-based model can correctly classify structures with 84.66% accuracy rate.

Medical image processing has become an integral part of disease diagnosis, where technological advancements have brought significant changes to this approach. In this review, a comprehensive comparison between Convolutional Neural Networks (CNN) and Support Vector Machines (SVM) in processing medical images is conducted. Automated medical analysis is becoming increasingly important due to issues of subjectivity in manual diagnosis and potential treatment delays. This research aims to compare the performance of Machine Learning (ML) in medical contexts using MRI, CT scan, and X-ray data. The comparison includes the accuracy rates of CNN and SVM algorithms, sourced from various studies conducted between 2018 and 2022. The results of the comparison show that CNN has higher average accuracy in processing MRI and X-ray data, with average values of 98.05% and 97.27%, respectively. On the other hand, SVM exhibits higher average accuracy for CT scan data, reaching 91.78%. However, overall, CNN achieves an average accuracy of 95.58%, while SVM's average accuracy is at 94.72%. These findings indicate that both algorithms perform well in processing medical data with high accuracy. Although based on these average accuracy rates, CNN demonstrates slightly better capabilities than SVM. Further research and development of more complex models are expected to continue improving the effectiveness of both approaches in disease diagnosis and patient care in the future.

Background Machine learning (ML) algorithm support vector machine (SVM) performed better than Thrombolysis in Myocardial Infarction (TIMI) score for ASIAN STEMI patients. However, Deep Learning (DL) effectiveness in the multiethnic ASIAN population has yet to be determined. DL has automatic learning of the feature from a given dataset without the need to conduct feature selection. However, the selected features by the algorithm is black box. Identifying features associated with mortality is essential to recognize characteristics of patients with high risk for better patient management. Purpose To develop a DL algorithm for in-hospital mortality in multiethnic STEMI patients using predictors identified from the SVM algorithm. To investigate DL performance constructed using predictors from SVM feature extraction and expert-recommended predictors. Methods We constructed four algorithms; a) DL and SVM algorithms with predictors identified from the SVM variable importance b) DL and SVM using predictors based on expert recommendation. We used registry data from the National Cardiovascular Disease Database of 11397 patient's. Fifty parameters including demographics, cardiovascular risk, medications and clinical variables were considered. The Area under the curve (AUC) is the performance evaluation metric. Algorithms were validated against the TIMI and tested using the same validation data. SVM variable importance with backward elimination was used to select and rank important variables. Results DL algorithms outperform SVM and TIMI on the validation dataset; i) DL with SVM selected predictors (15 predictors, AUC = 0.97), ii) DL with expert-recommended predictors (16 predictors, AUC = 0.96), iii) SVM with selected predictors (15 predictors, AUC = 0.92), iv) SVM with expert-recommended predictors (AUC = 0.89) and TIMI (AUC = 0.82). Common predictors across SVM feature selection, expert-recommendation and TIMI are: age, heart rate, Killip class, fasting blood glucose, systolic blood pressure, comorbid diseases and ST-elevation. SVM feature selection also identified diuretics, PCI and pharmacotherapy drugs as predictors that improve mortality prediction in STEMI patients. Our findings suggest that the TIMI score underestimates patients risk of mortality. DL algorithm using selected predictors classified 35% of nonsurvival patients as high risk (risk probabilities >50%) compared to only 12.7% nonsurvival patients by TIMI (score >5) (Figure below). Conclusions In the ASIAN population, patients with STEMI can be better classified using the DL algorithm compared to the ML and TIMI score. Combining ML feature selection with DL allows the identification of distinct factors in a unique ASIAN population for better mortality prediction than relying solely on an expert recommendation as it is a very subjective approach. Continuous validation on population-specific algorithms using DL and ML is needed before implementing in a real clinical setting. Funding Acknowledgement Type of funding sources: Public grant(s) – National budget only. Main funding source(s): Technology Development Fund 1 TIMI performance on validation setDL performance on validation set

With the development of the Internet of Things (IoT) and virtual reality (VR) technology, the demand for high-precision gesture intelligent analysis of a human–machine interaction module for IoT–VR systems is increasing. Therefore, random forest (RF) and convolution neural network (CNN) algorithms are used in this study to build an intelligent gesture recognition model. The experiments were conducted to test the application performance of the design model. The test results show that the qualification rate of the analytical model designed in this study is significantly higher than that of the comparative model. When the threshold is determined to be 43.26 mm, the analytical qualification rates of the RF-CNN (the method of combining RF with CNN algorithms), faster regions with CNN features (Faster-RCNN), and RF models are 82.41%, 76.10%, and 59.10%, respectively. The calculation time of the RF–CNN model is between the two comparative models. From the test data, it can be observed that the research results have certain significance for improving the accuracy of gesture machine recognition technology in China’s VR Internet of Things (IoT) system.

BackgroundMachine learning (ML) algorithm support vector machine (SVM) performed better than Thrombolysis in Myocardial Infarction (TIMI) score for ASIAN STEMI patients. However, Deep Learning (DL) effectiveness in the multiethnic ASIAN population has yet to be determined. DL has automatic learning of the feature from a given dataset without the need to conduct feature selection. However, the selected features by the algorithm is black box. Identifying features associated with mortality is essential to recognize characteristics of patients with high risk for better patient management.PurposeTo develop a DL algorithm for in-hospital mortality in multiethnic STEMI patients using predictors identified from the SVM algorithm. To investigate DL performance constructed using predictors from SVM feature extraction and expert-recommended predictors.MethodsWe constructed four algorithms; a) DL and SVM algorithms with predictors identified from the SVM variable importance b) DL and SVM using predictors based on expert recommendation. We used registry data from the National Cardiovascular Disease Database of 11397 patient's. Fifty parameters including demographics, cardiovascular risk, medications and clinical variables were considered. The Area under the curve (AUC) is the performance evaluation metric. Algorithms were validated against the TIMI and tested using the same validation data. SVM variable importance with backward elimination was used to select and rank important variables.ResultsDL algorithms outperform SVM and TIMI on the validation dataset; i) DL with SVM selected predictors (15 predictors, AUC = 0.97), ii) DL with expert-recommended predictors (16 predictors, AUC = 0.96), iii) SVM with selected predictors (15 predictors, AUC = 0.92), iv) SVM with expert-recommended predictors (AUC = 0.89) and TIMI (AUC = 0.82). Common predictors across SVM feature selection, expert-recommendation and TIMI are: age, heart rate, Killip class, fasting blood glucose, systolic blood pressure, comorbid diseases and ST-elevation. SVM feature selection also identified diuretics, PCI and pharmacotherapy drugs as predictors that improve mortality prediction in STEMI patients. Our findings suggest that the TIMI score underestimates patients risk of mortality. DL algorithm using selected predictors classified 35% of nonsurvival patients as high risk (risk probabilities >50%) compared to only 12.7% nonsurvival patients by TIMI (score >5) (Figure below).ConclusionsIn the ASIAN population, patients with STEMI can be better classified using the DL algorithm compared to the ML and TIMI score. Combining ML feature selection with DL allows the identification of distinct factors in a unique ASIAN population for better mortality prediction than relying solely on an expert recommendation as it is a very subjective approach. Continuous validation on population-specific algorithms using DL and ML is needed before implementing in a real clinical setting.Funding AcknowledgementType of funding sources: Public grant(s) – National budget only. Main funding source(s): Technology Development Fund 1TIMI performance on validation setDL performance on validation set

This study examined whether adaptive behaviour, emotional and behavioural challenges, and social skills, respectively, moderated the effect of a movement skill intervention on movement skills among preschool aged children with autism spectrum disorder. Twenty-seven participants with autism spectrum disorder (N = 13 experimental) between 3 and 5 years of age participated in a 12-week fundamental movement skill intervention. Movement skills were assessed at baseline and post-test. Adaptive behaviour, emotional and behavioural challenges, and social skills were assessed at baseline. A repeated-measures analysis of variance tested the group by time effect on movement skills. Three separate moderation analyses were then run to test the moderating effect of adaptive behaviour, emotional and behavioural challenges, and social skills, respectively, on the relationship between group assignment and movement skills at the post-test. The experimental group significantly improved their movement skills following the intervention (p = 0.02, ηp2=.19). The moderation analyses showed that adaptive behaviour (b(SE) = 0.86 (0.41), p < 0.05) and emotional and behavioural challenges (b(SE) = −1.5 (0.8), p = 0.06) at baseline moderated the association between group and post-test movement skills, when controlling for baseline movement skills. These findings may help caregivers and clinicians individualize treatment plans in regard to movement skill interventions for preschool-aged children with autism spectrum disorder.Lay abstractIt is common for children with autism spectrum disorder to experience delays in their movement skills. These skills are important for participation in play and physical activity. Previous research has found that movement skills can be improved with movement skill interventions. This study explored the behavioural factors of young children with autism spectrum disorder that make them most likely to improve their movement skills following a 12-week intervention. The study found that children with higher levels of adaptive behaviour and lower levels of emotional and behavioural challenges at the start of the intervention were more likely to have greater improvements in their movement skills following the intervention. These findings may help clinicians and caregivers plan which types of interventions are best suited for individual children with autism spectrum disorder.

The aim of this study was to investigate the value of single-photon emission computed tomography (SPECT) based on the convolutional neural network (CNN) algorithm in thyroid diseases. Thirty-five patients with thyroid disease from the hospital were selected as the observation group, and another 35 healthy volunteers were selected as the control group. The constructed model of SPECT based on the CNN algorithm was compared with the backpropagation neural network (BPNN) algorithm, which was then applied to the SPECT of 35 patients with thyroid disease. It turned out that as the number of iterations increased, the parameter training of CNN was gradually sufficient, the network model was continuously optimized, and the accuracy gradually increased. From the data results, the Dice value of the proposed CNN algorithm was higher than that of the BPNN algorithm and the segmentation effect was relatively good. The visual index of the thyroid/neck of the observation group (2.68 ± 1.32) was remarkably inferior to that of the control group (12.347.54) ( P &lt; 0.05 ). The visual index of the thyroid/submandibular gland in the observation group (1.02 ± 0.41) was remarkably inferior to that of the control group (8.89 ± 4.86) ( P &lt; 0.05 ). The visual index of the thyroid/parotid gland in the observation group (1.04 ± 0.58) was remarkably inferior to that of the control group (8.53 ± 4.25) ( P &lt; 0.05 ). In addition, 99mTcO4-SPECT had a sensitivity of 95.2%, a specificity of 90.3%, and an accuracy of 91.5% in the diagnosis of thyroid diseases. The area under the curve of the receiver operating characteristic curve for 99mTcO4-SPECT diagnosis of thyroid disease is 0.958, and the 95% confidence interval is 0.834∼1. In summary, the SPECT based on the CNN algorithm proposed in this study has a good segmentation effect and can accurately locate the anatomical information of thyroid diseases, which can replace the traditional diagnostic methods for the diagnosis of thyroid diseases.

Emotion recognition from speech plays a crucial role in enhancing human–computer interaction by enabling systems to interpret and respond to users’ emotional states. This study develops and evaluates a Speech Emotion Recognition (SER) system using three machine learning techniques; Support Vector Machines (SVM), Multilayer Perceptron (MLP), and Convolutional Neural Networks (CNNs). The system is trained and tested on the RAVDESS dataset, which contains 1,440 professionally recorded audio samples representing a wide range of emotions. Our approach involves careful preprocessing of the audio signals, extraction of key acoustic features, and comparative performance evaluation of the three models using standard metrics. Results show that each model exhibits unique strengths and limitations, with CNNs achieving the most robust feature learning and generalization. The study underscores the importance of diverse feature representation for accurate emotion classification and provides insight into how different model architectures handle emotional nuances in speech. Identified challenges such as dataset diversity, feature selection, and computational complexity are discussed, along with recommendations for future research to improve SER systems’ real-world adaptability. This work contributes to ongoing efforts toward developing emotionally aware technologies that can enhance natural human–machine communication.