Delays, energy-constrained, and dynamic environments continue to present a challenge to wireless sensor networks (WSNs), which are an infrastructure in the next generation of smart infrastructure. The traditional routing and scheduling techniques are inadequate to the management of such issues since they are fixed-point and lack flexibility. A new framework, named Artificial Intelligence-Driven Cognitive Delay-Aware Routing and Scheduling Framework (AICD-RSF), is presented in this paper; it entails the use of context-aware routing that depends on graph attention network (GAT), delay prediction relying on spiking neural network (SNN), Belief Rule-Based Trust Evaluation (BRB-TL), time-slot preemption with the use of quantum-inspired particle swarm optimization (QPSO), and decentralized model optimization with the help of AICD-RSF is demonstrated to work outstanding against the classical protocols like AODV and DSR in a simulated NS-3 network scenario. The end-to-end delay had gone down by up to 51.94 and the percentage rate of delivering the packets up to 98.3 and the use of energy was reduced by up to 41.1. The mean absolute error of delay prediction also had a possibility of 2.96 ms, and this was able to confirm the efficiency of inference of the SNN model. In addition to that, the use of trust-based path selection was more secure, and the federated learning model was above 92.7% accurate and with low communication overhead. The model provides a solution to the key failures of the existing WSN models, including offering low-power, self-learning, and scalable one, which can be employed in high-priority real-time system applications, such as battlefield surveillance, smart healthcare, and critical infrastructure.

Efficient heat exchanger design is paramount in optimizing chemical processing operations, where energy consumption and cost considerations are crucial. Traditional design approaches rely on empirical correlations and iterative simulations, often resulting in suboptimal solutions due to the complex and nonlinear nature of heat transfer phenomena. In this study, the research proposes a novel approach to enhance heat exchanger design using an autoencoder model for predicting both efficiency and cost. The autoencoder model, a type of artificial neural network, is trained on a comprehensive dataset encompassing various operating conditions, geometric configurations, and material properties of heat exchangers. By learning the underlying patterns and relationships within the data, the autoencoder can effectively capture the nonlinear mappings between design parameters and performance metrics. Through extensive validation and testing, the proposed autoencoder model demonstrates superior accuracy in predicting heat exchanger efficiency and cost compared to conventional methods. Furthermore, the model enables rapid exploration of design alternatives and sensitivity analysis, facilitating informed decision-making in the design phase. By leveraging machine learning techniques, this approach offers a promising avenue for advancing heat exchanger design towards higher efficiency and lower cost in chemical processing applications. The framework demonstrates considerable promise in bolstering efficiency and enhancing economic viability, boasting a correlation coefficient of 0.98171 and a normalized root mean square error (NRMSE) of 0.001523.

Circuits on printed circuit boards (PCBs) must be very reliable and of high quality, especially in the current dynamically changing electronics production line. This paper outlines a novel approach toward using the Faster Region–Convolutional Neural Network (Faster R-CNN) deep learning model for PCB fault identification and categorisation. A modelling process that consists of model construction, training, evaluation, and dataset generation was developed. A well-labelled and well-trained heterogeneous dataset with various types of PCB faults including various flaws such as spurs, open circuits, mouse bites, missing holes, shorts, and spurious copper was used in this study. Data augmentation techniques were employed to improve the data. After being adjusted and assessed, the Faster R-CNN model produced some excellent performance metrics. It had an accuracy of 0.912, precision of 0.905, recall of 0.930, F1 score of 0.917, and mean average precision (mAP) of 0.919. The inference outcomes showcase the capacity of the model in swiftly identifying various faults so that efficient actions in quality control processes can be determined on time. This work shows how complex deep learning algorithms can be applied to support PCB inspection and, in the long run, enhance manufacturing efficiency and product reliability.

Groundwater quality assessment is a paramount aspect of ensuring the availability of safe drinking water. The conventional reliance on individual parameter thresholds often overlooks intricate interdependencies within the dataset. To overcome this, deep learning algorithms are employed to automatically extract meaningful features from multidimensional data. This innovative approach aims to capture complex relationships between water quality parameters that may be missed by traditional methods. The research identifies a significant gap in current groundwater quality assessment methodologies, emphasizing the need for a more data-driven approach. This research addresses the limitations of traditional methods by introducing a pioneering approach that integrates deep learning and hierarchical cluster analysis to identify comprehensive water quality indicators. The study collects data from diverse monitoring wells, encompassing chemical, physical, and biological parameters. By applying deep cluster analysis to the feature-extracted data, latent patterns and relationships among water quality parameters are unveiled. This clustering method reveals hidden structures within the dataset, leading to the identification of water quality indicators that consider both individual parameters and their interactions. The proposed method in this research offers an understanding of groundwater quality dynamics, contributing to the advancement of water resource management strategies. The results of the deep cluster analysis provide a more comprehensive and accurate representation of groundwater quality, enabling better-informed decision-making for sustainable water resource utilization.

Groundwater (GW) availability is at risk due to over-extraction, pollution, and climate change, despite their vital role in satisfying the world's freshwater needs. Decisions made using outdated, under-data-driven models for groundwater management are not always the best option. Traditional approaches often fail to tackle groundwater systems' intricacies and ever-changing nature, even if groundwater management has come a long way. Groundwater over-extraction, pollution, and depletion are consequences of ineffective monitoring, prediction, and management, which endangers environmental sustainability and water security.The rising problems of Sustainable Groundwater Management (SGM) and development in the context of global freshwater demand and climate change were addressed in this study. A revolutionary technique for predicting models and the Water Quality Assessment (WQA) by employing the potential of Deep Learning (DL), a type of Artificial Intelligence (AI). Then, the limitations faced by the existing Groundwater Management methods (GM) in predicting the Variations in the GW levels were identified, and it also predicted the quick detection of the WQ (Water Quality) deterioration. The application of DL algorithms offers precise prediction and early detection, and this study also aims to fill the gaps by executing DL on past and present data. By addressing the drawbacks of these traditional methods, Pattern Recognition (PR) and analysis in the DL can revolutionize these procedures. For predicting the modelling of GW levels, the Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and particularly Long Short Term Memory (LSTM) networks are employed in this study.For WQA, Deep CNN (DCNN) are employed. The hidden patterns are revealed within the large datasets by applying Deep Transformer Analysis (DTA), which supports specific management approaches. The outcomes demonstrated the revolutionary impact of DL techniques. The LSTM networks facilitated the precise predictions for GW variations and Proactive Resource management. CNN accurately determined the GQA, detecting indicators like PH and level of pollutants early. The DTA contributed to classifying the GW quality levels effectively and optimizing the management techniques. The precise predictive models for GW level variations and accurate WQA parameters were presented in this study by applying these advanced techniques to historical and real-time data. The proactive resource management, early detection capabilities, and sustainability of GW resources facilitate the transformative potential of DL and the outcomes obtained. The enhanced accuracy rate of 97.2%, F1 score rate of 96.2%, MAE (Mean Absolute Error) rate of 0.8%, RMSE (Root Mean Square Error) of 1.1%, loss rate of 0.04% were attained by the suggested CNN-DTA model when compared to other current techniques.

This research work explores the integration of medical and information technology, particularly focusing on the use of data analytics and deep learning techniques in medical image processing. Specifically, it addresses the diagnosis and prediction of fetal conditions, including Down Syndrome (DS), through the analysis of ultrasound images. Despite existing methods in image segmentation, feature extraction, and classification, there is a pressing need to enhance diagnostic accuracy. Our research delves into a comprehensive literature review and presents advanced methodologies, incorporating sophisticated deep learning architectures and data augmentation techniques to improve fetal diagnosis. Moreover, the study emphasizes the clinical significance of accurate diagnostics, detailing the training and validation process of the AI model, ensuring ethical considerations, and highlighting the potential of the model in real-world clinical settings. By pushing the boundaries of current diagnostic capabilities and emphasizing rigorous clinical validation, this research work aims to contribute significantly to medical imaging and pave the way for more precise and reliable fetal health assessments.

Physical situations that are duplicated in virtual settings are what the term "digital twin" refers to. Utilizing the Internet of Things and sensors to improve microgrid operation, the Microgrid Digital Twin (MGDT) exhibits bidirectional data sharing and sophisticated communication characteristics. Smart grid functionality is enhanced, limits are set in real-time, and data is securely stored by MGDT. It directs the planning and execution phases of microgrid operations. Concurrently, industry and transportation innovation is propelled by the Industrial Revolution. AI-driven ground-dependent controls, communication systems, and sensors are essential for breakthroughs in unmanned vehicle safety. This abstract clarifies how important digital twins more specifically, MGDTs are to system operations optimization. In addition to highlighting technological advancement and the use of AI to ensure the safety of unmanned vehicles, it provides insights into the potentially revolutionary applications of digital twins across a range of industries.

Urban areas worldwide are increasingly at risk from hydrogeological hazards, leading to severe consequences. Urban flooding and mismanagement of water resources, resulting in riverine flooding, are primary contributors to this risk. Utilizing big data, including mobile phone signals collected at high frequencies, alongside administrative data, is essential for developing risk exposure indicators in smaller urban regions. Accurately assessing human traffic flows and movements is crucial for mitigating the impacts of natural disasters and ensuring a high quality of life in smart cities. However, comprehensive solutions to these challenges are lacking in many countries. Therefore, this study focuses on analyzing the impact of traffic data flow analysis in hydrogeological risk areas. The study employs mobile phone signals as big data to analyze traffic flows and forecast exposure risks to aid decision-making. To ensure data reliability, a circle search integrated fully connected conditional neural network (CS-ConNN) is used for data cleaning, categorizing mobile phone signal data into normal, empty, and garbage. Additionally, the study uses a deep recurrent neuro fuzzy system (DRNFS) to analyze the compound seasonality of circulation flow data and forecast risks, providing alerts to individuals transiting through affected areas. The model is validated through a case study of "Mandolossa," and developed area prone to inundating near Brescia, using hourly data from September 2020 to August 2021. Experimental results and cross-validation demonstrate a forecasting accuracy of 98.975%.

In this paper, we present a comprehensive system model for Industrial Internet of Things (IIoT) networks empowered by Non-Orthogonal Multiple Access (NOMA) and Mobile Edge Computing (MEC) technologies. The network comprises essential components such as base stations, edge servers, and numerous IIoT devices characterized by limited energy and computing capacities. The central challenge addressed is the optimization of resource allocation and task distribution while adhering to stringent queueing delay constraints and minimizing overall energy consumption. The system operates in discrete time slots and employs a quasi-static approach, with a specific focus on the complexities of task partitioning and the management of constrained resources within the IIoT context. This study makes valuable contributions to the field by enhancing the understanding of resourceefficient management and task allocation, particularly relevant in real-time industrial applications. Experimental results indicate that our proposed algorithm significantly outperforms existing approaches, reducing queue backlog by 45.32% and 17.25% compared to SMRA and ACRA while achieving a 27.31% and 74.12% improvement in QnO. Moreover, the algorithm effectively balances complexity and network performance, as demonstrated when reducing the number of devices in each group (Ng) from 200 to 50, resulting in a 97.21% reduction in complexity with only a 7.35% increase in energy consumption. This research offers a practical solution for optimizing IIoT networks in real-time industrial settings.

One serious health problem is breast cancer for women worldwide, and detecting it early can significantly improve treatment outcomes. Various methods and technologies are used to detect breast cancer, but finding the most accurate and reliable method remains a challenge. In this study, we focused on two popular machine learning algorithms, the SVM and the Decision Tree, to see which one is better at predicting the risk of breast cancer. Both of these methods have been used in similar tasks, but it is not always clear which one provides better results. While there has been some research comparing these algorithms, there is a need for more detailed studies using modern datasets to ensure the results are accurate and relevant to current medical practices. Our goal was to compare the effectiveness of the two algorithms in detecting breast cancer using a training dataset. We used a dataset with 10 samples for each algorithm to train and test their performance. SVM achieved an accuracy of 95.7% in detecting breast cancer, which was higher than the 93.07% accuracy of the Decision Tree algorithm. We used a significance level of $p<0.05$ to ensure our findings are statistically significant. The Support Vector Machine proved to be more accurate than the Decision Tree in predicting breast cancer risk.

Through the integration of AI and IoT, the digital twin transforms industrial sectors by virtually portraying physical systems. Simulation and the application of lifecycle management improve decision-making. In this paper, a virtual prototype system a digital twin framework that integrates robotic devices is proposed. Created using debugging platforms, they track every robotic activity, supported by real-time microcontroller structural design systems. Machine learning methods are the fundamental engine of the digital twin system. Because of this connection, robotic actions may be seamlessly controlled and monitored, guaranteeing effectiveness and adaptability in changing contexts. Robotics has advanced significantly with the combination of digital twin technology, machine learning, and microcontroller systems, offering improved performance and versatility in a range of applications.

In this study, we introduce a novel real-time approach for detecting abnormal behaviors in online social networks, leveraging both dynamic user activities and their associated profiles through Convolutional Neural Networks (CNN). Social networks, which serve as hubs for communication, discussion, and multimedia sharing, amass a plethora of user data. This vast reservoir of information, while invaluable for genuine interactions, is susceptible to exploitation by malicious entities. Despite numerous previously proposed detection methods, the challenge of ensuring security persists. Our distinctive framework, rigorously tested using an extensive dataset sourced from the web and executed via the CNN toolbox in MATLAB, consistently demonstrates an impressive 99.9% classification accuracy. This achievement not only underscores the method's effectiveness but also marks a significant stride towards proactively identifying and neutralizing potential threats in digital social platforms.

In healthcare, data mining algorithms are utilized to make people's lives better by predicting diseases and trying to diagnose them faster than most doctors. When the middleman is eliminated, as it is with computerized medical insurance, there is an unbroken line of communication between the insurance company and the insured. Predicting the premium of medical insurance is a major source of worry. The only way for a health insurance provider to turn a profit is to receive more in premium payments than it pays out in claims. Linear Support Vector Machines (LSVM)are developed for Premium Prediction in the Well-beingAssurance Sector. Eleven different criteria were used to train and evaluate LSVM. Experimental results showed a 99% accuracy, and the researchers analysed the effectiveness of the algorithm using success metrics.

Fog computing is playing a vital role in data transmission to distributed devices in the Internet of Things (IoT) and another network paradigm. The fundamental element of fog computing is an additional layer added between an IoT device/node and a cloud server. These fog nodes are used to speed up time-critical applications. Current research efforts and user trends are pushing for fog computing, and the path is far from being paved. Unless it can reap the benefits of applying software-defined networks and network function virtualization techniques, network monitoring will be an additional burden for fog. However, the seamless integration of these techniques in fog computing is not easy and will be a challenging task. To overcome the issues as already mentioned, the fog-based delay-sensitive data transmission algorithm develops a robust optimal technique to ensure the low and predictable delay in delay-sensitive applications such as traffic monitoring and vehicle tracking applications. The method reduces latency by storing and processing the data close to the source of information with optimal depth in the network. The deployment results show that the proposed algorithm reduces 15.67 ms round trip time and 2 seconds averaged delay on 10 KB, 100 KB, and 1 MB data set India, Singapore, and Japan Amazon Datacenter Regions compared with conventional methodologies.

A vehicular ad hoc IoT network (VA-IoT) plays a key role in exchanging the constrained networked vehicle information through IPv6-enabled sensor nodes. It is noteworthy to understand that vehicular IoT is interconnection of vehicular ad hoc networks with the support of constrained IoT devices. Routing protocols in VAN-IoT are designed to route the vehicular traffic in the distributed environments. In addition, VAN-IoT is designed to enhance road safety by reducing the number of road accidents through reliable data transmission. Routing in VAN-IoT has a unique dynamic topology, frequent spectrum, and node handover with restricted versatility. Hence, it is very crucial to design the hybrid reactive routing protocols to ensure the network throughput and data reliability of the VAN-IoT networks. This paper aims to propose an AI-based reactive routing protocol to enhance the performance of the network throughput, minimize the end-to-end delay with respect to node mobility, spectrum mobility, link traffic load and end-to-end network traffic load while transmitting the vehicular images. In addition, the performance of the proposed routing protocol in terms of image transmission time is being compared with the existing initiative-taking- and reactive-based routing protocols in vehicular ad hoc IoT (VA-IoT) networks.

A secured platform is a critical component of digital governance, as it helps to ensure the privacy, security, and reliability of the electronic platforms and systems used to manage and deliver public services. Interoperability and data exchange are essential for digital governance, as they enable different government agencies and departments to share data, information, and resources seamlessly, regardless of the platforms and technologies they use. In this paper, we build a secure platform to enhance the trustworthiness of digital governance interoperability and data exchange using blockchain and deep learning-based frameworks. Initially, an optimal blockchain leveraging approach is designed using the bonobo optimization algorithm to authenticate data generated from smart city environments. Furthermore, we introduce the integration of a lightweight Feistel structure with optimal operations to enhance privacy preservation. This integration provides two levels of security and ensures interoperability and double-secured data exchange in digital governance systems. In addition, we utilize a deep reinforcement learning (DRL) model to detect and prevent intrusions such as fraud/corruption in the smart city data. This approach enhances transparency and accountability in accessing the data and shows its predominance over other cutting-edge techniques on two benchmark datasets, BoT-IoT and ToN-IoT. Furthermore, the effectiveness of the framework in real-time scenarios has been demonstrated through two case studies. Overall, our proposed framework provides a trustworthy platform for digital governance, interoperability, and data exchange, addressing the challenges of privacy, security, and reliability in managing and delivering public services.

Nowadays, the integration of conventional analytical approaches with smartphones has been developed novel, emerging and affordable devices for improving on-site detection platforms in the fields of food safety. Smartphone-based aptasensors as the next generation of portable aptasensing technique has attracted considerable attention as it offers a semi-automated user interface that can be exploited by inexpert characters. Wireless data transferability is an undeniable advantage that home-testing platforms have as well as it can suggest high computational power. In addition, these types of biodevices can provide real-time monitoring in terms of exchanging digital networks in real-time. To elaborate, the ability of smartphones to connect through the Internet is one of the most critical advantages of smartphone-based aptasensor that can be uploaded to Cloud databases and results can be disseminated as spatio-temporal maps across the globe. This review focused on the recent progress and technical breakthroughs of aptasensor on the smartphone as a groundbreaking enterprise in the field of biochemical analysis, importantly in the aspect of the combination of different types of biosensors including electrochemical, optical and colorimetric. In our opinion, this review can broaden our understanding of using smartphones as a portable sensing approach by addressing the current challenges and future perspectives.

The satellite communication is embellished constantly by providing information, ensuring security, and enables the communication among huge at a particular time efficiently. The satellite navigation helps in determining the people's location. Global development, natural disasters, change in climatic conditions, agriculture crop growth, etc., are monitored using satellite observation. Hence, the satellite includes detailed information data, and it must be protected confidentially. The field of the satellite is enhanced at an astonishing pace. Satellite data play an important role in this modern world; hence, the onboard-satellite data must secure through the proper selection of error detection and estimation schema. Lightweight deep learning algorithm based on Extended Kalman Filter (KFK) is proposed to detect and estimate onboard pointing error such as an error in attitude and orbit. The Extended Kalman Filter (EKF) is widely used in the satellite system. EKF is utilized in this proposed model to detect the onboard pointing error such as attitude and orbit determination. An autonomous estimation of orbit position is possible through space-borne gravity. The information obtained through the observation of satellite data is compared with the accurate gravity model in detecting the error. The utilization of EKF reduces the dependence of the ground tracking system in satellite determination. The orbital altitude and orbital position are the most important challenges faced in the satellite determination system. The satellite model using the Extended Kalman Filter is an optimum method in estimating the orbital parameters. The errors in the linearization process are detected, and this can be overcome through the proper selection of linear expansion point with the EKF algorithmic model with the Jacobian matrix calculation. The results show that the EKF implementation helps in attaining better accuracy than other methodologies. Its contribution is enormous to many space missions, autonomous rendezvous and docking for manned and unmanned missions (e.g., ISS operations and beyond, in-orbit servicing, and in-orbit refueling), routine satellite OD operations, orbital debris removal systems, Space Situational Awareness (SSA) operations, and others.