Prachi Janrao

Living without effective communication poses significant challenges for humans. Individuals employ various methods to convey and share their thoughts and ideas between the sender and receiver. Two of the most prevalent means of communication are verbal speech, which relies on auditory perception, and non-verbal communication through gestures involving bodily movements such as hand gestures and facial expressions. Sign language, specifically categorized as a gestural language, is a unique form of communication that relies on visual perception for understanding and expression. While many individuals incorporate gestures into their communication, for deaf individuals, sign language is often their primary and essential means of communication. Individuals who are deaf and dumb rely on communication to interact with others, gain knowledge, and engage in their surroundings. Sign language serves as a crucial link that reduces the distance between them and the broader society. In order to enhance this communication, we've created models with the ability to identify sign language gestures and translate them into conventional text. Through the training of these models on a dataset employing neural networks, remarkable outcomes have been attained. This technology enables individuals, without prior knowledge of sign language, to understand the intentions and messages of individuals with disabilities, fostering greater inclusivity and accessibility in our society. Three algorithms were used to achieve this work and the findings show very good outcomes, i.e. Random Forest at 98%, Logistic Regression at 99%, and Decision Tree at 91%. Keywords: Machine Learning, Sign Language, Random Forest, Neural Network, Logistic Regression Deaf and Dumb, Decision Tree

Autism spectrum disorder (ASD) poses a complex challenge to researchers and practitioners, with its multifaceted etiology and varied manifestations. Timely intervention is critical in enhancing the developmental outcomes of individuals with ASD. This paper underscores the paramount significance of early detection and diagnosis as a pivotal precursor to effective intervention. To this end, integrating advanced technological tools, specifically eye-tracking technology and deep learning algorithms, is investigated for its potential to discriminate between children with ASD and their typically developing (TD) peers. By employing these methods, the research aims to contribute to refining early detection strategies and support mechanisms. This study introduces innovative deep learning models grounded in convolutional neural network (CNN) and recurrent neural network (RNN) architectures, employing an eye-tracking dataset for training. Of note, performance outcomes have been realised, with the bidirectional long short-term memory (BiLSTM) achieving an accuracy of 96.44%, the gated recurrent unit (GRU) attaining 97.49%, the CNN-LSTM hybridising to 97.94%, and the LSTM achieving the most remarkable accuracy result of 98.33%. These outcomes underscore the efficacy of the applied methodologies and the potential of advanced computational frameworks in achieving substantial accuracy levels in ASD detection and classification.

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder characterized by difficulties in social communication and repetitive behaviors. The exact causes of ASD remain elusive and likely involve a combination of genetic, environmental, and neurobiological factors. Doctors often face challenges in accurately identifying ASD early due to its complex and diverse presentation. Early detection and intervention are crucial for improving outcomes for individuals with ASD. Early diagnosis allows for timely access to appropriate interventions, leading to better social and communication skills development. Artificial intelligence techniques, particularly facial feature extraction using machine learning algorithms, display promise in aiding the early detection of ASD. By analyzing facial expressions and subtle cues, AI models identify patterns associated with ASD features. This study developed various hybrid systems to diagnose facial feature images for an ASD dataset by combining convolutional neural network (CNN) features. The first approach utilized pre-trained VGG16, ResNet101, and MobileNet models. The second approach employed a hybrid technique that combined CNN models (VGG16, ResNet101, and MobileNet) with XGBoost and RF algorithms. The third strategy involved diagnosing ASD using XGBoost and an RF based on features of VGG-16-ResNet101, ResNet101-MobileNet, and VGG16-MobileNet models. Notably, the hybrid RF algorithm that utilized features from the VGG16-MobileNet models demonstrated superior performance, reached an AUC of 99.25%, an accuracy of 98.8%, a precision of 98.9%, a sensitivity of 99%, and a specificity of 99.1%.