Autism Spectrum Disorder (ASD) is a general neurodevelopmental condition that requires early and accurate diagnosis. Electroencephalography (EEG) signals are reliable biomarkers for ASD detection and diagnosis. A recent Deep Learning (DL) model called Resting-state EEG-based Hybrid Graph Convolutional Network (Rest-HGCN) has been developed for this purpose. However, a challenge in ASD diagnosis is the limited availability of EEG data, leading to imbalanced classes and ineffective model training. To address this issue, a new approach is proposed in this paper, which involves a generative model for EEG data augmentation. A novel Dual Encoder-Balanced Conditional Wasserstein Generative Adversarial Network (DEBCWGAN) is designed to produce fine synthetic minority-class EEG examples and augment the original training dataset. This model integrates the Variational Auto-Encoder (VAE) and balanced conditional Wasserstein GAN. Initially, EEG signals for ASD in the training dataset are pre-processed as Differential Entropy (DE) features and split into different segments. Each feature segment is processed in the temporal and the spatial domain depending on the electrode place. Then, twin encoders are trained to capture both spatial and temporal information from these features, concatenate them as Latent Variables (LVs), and provide them to the decoder to produce synthetic EEG examples. Additionally, gradient penalty and L2 regularization are used to speed up convergence and prevent overfitting effectively. Further, the augmented dataset is used to train the Rest-HGCN for ASD detection, enhancing its robustness and generalizability. Finally, test outcomes demonstrate that the DEBWGAN-GP-Rest-HGCN on the EEG Dataset for ASD and ABC-CT dataset achieves 91,6 % and 88,1 % accuracy, respectively compared to the Rest-HGCN, AlexNet, K-Nearest Neighbor (KNN) and Support Vector Machine (SVM)

Diabetic foot ulcer (DFU) is one of the most expensive and debilitating complications of diabetes. According to procedures developed by the National Institute of Health and Clinical Excellence, early and effective treatment of DFU can minimize the severity of complications, such as unnecessary amputations, and improve overall quality of life. In this paper, a stacked parallel convolution layers based Convolution Neural Network (CNN) is proposed, known as DFU MobileNet, to classify skin infected with DFU against normal skin. The main objective of this work is to develop a DFU recognition system that accurately identifies infected skin. DFU MobileNet consists of three blocks of parallel convolution layers, each with a unique kernel size to extract local and global features distinctly. Using the DFUC 2020 dataset, the proposed DFU MobileNet outperformed existing state-of-the-art models, achieving an accuracy of 92.2% using CNN DenseNet, 95.4% using MobileNet, and 97.8% when combining DenseNet and MobileNet.

6G networks are booming, and they will transform healthcare; ultra-low latency, massive connections, and intelligent services will finally reach critical applications. Real-time performance, standardization, and scalability of healthcare networks are impacted by having various categories of devices, changing workloads, and changing resource requirements. This paper suggests a new AI-based method for standardized 6G healthcare systems, referred to as the Cognitive Autonomous Resource and Edge Collaboration Framework (CARE-6G). The use of cognitive AI agents together with edge-cloud cooperation in CARE-6G enables automated prediction, allocation, and optimization of computing, storage, and networking resources. The framework is constructed hierarchically such that edge nodes perform low-latency processing, while cloud infrastructure performs big-scale analytics. AI-based predictive orchestration ensures that the needs for workloads and healthcare services can shift. The experiments indicated that CARE-6G is 35% quicker, 30% more resource-efficient, and 27% more reliable than the existing practices. When compared to the best methods available, CARE-6G was 39% faster, 30% better at using resources, 27% more reliable, 25% less power-hungry, and 15% better at getting things done.

Recent years have seen a significant increase in the use of artificial intelligence (AI) and machine learning (ML) concepts across a variety of academic domains. AI's major objective is to build intelligent systems and give machines human intelligence. Artificial intelligence is a tool for creating systems, making judgements, solving problems, learning, and linguistic intelligence, as well as for imitating human conduct. Electrical and computer engineers are at the forefront of intellectual creativity as they participate in the planning, creation, evaluation, and production processes for newer generations of gadgets and technology. Even if these professionals want to grow, their objectives might conflict with the consequences of artificial intelligence, which are continually expanding. The practice of Artificial Intelligence (AI) and Machine Learning (ML) applications in industrial industries that have a significant influence on sustainability and the environment, such as renewable energy, smart grids, the catalyzed industry, and power storage and distribution The main popular approaches are artificial neural networks and Machine learning. Demand for energy is skyrocketing at a higher pace than production in the industry between 2004 and 2017, implying a decline in energy efficiency (EE). Under the premise of steady future output, an explicit energy efficiency enhancement target of 26% from 2017 and 2050 is set. Request access from your librarian to read this chapter's full text.

Today's wealth and value are data. Data, used sensibly, are making wonders to make wise decisions for individuals, corporates, etc. The era of spending time with an individual to understand them better is gone. Individual's interests, requirements are identified easily by observing the activities an individual performs in social media. Social media, started as a tool for interaction, has grown as a platform to make and promote business. Social media content is unavoidable as the data that are going to be dealt with is huge in volume, variety, and velocity. The demand for using machine learning in analysing social media content is increasing at a faster pace in identifying influencers, demands of individuals. However, the real complexity lies in making the data from social media suitable for analysis. The type of data from social media content may be audio, video, image. The chapter attempts to give a comprehensive overview of the various pre-processing methods involved in dealing the social media content and the usage of right algorithms at the right time with suitable case examples. Request access from your librarian to read this chapter's full text.